Conversation topic discovery: A new conversation topics endpoint (GET /v1/convai/agents/{agent_id}/topics) returns the latest topic discovery results for a given agent, surfacing recurring themes across conversations. The list conversations endpoint now accepts a topic_ids query parameter to filter conversations by discovered topic.
Knowledge base content search: A new search knowledge base endpoint (GET /v1/convai/knowledge-base/search) provides fuzzy text search over knowledge base document content. Results include highlighted snippets with SearchHighlightSegment objects and support cursor-based pagination with configurable page sizes (up to 100, default 30). Filter by document type with the optional types parameter.
Flexible branch merging: The merge branch endpoint no longer restricts merges to the main branch -- any branch can now be used as a merge target. A new optional force boolean parameter overrides timestamp-based conflict resolution when set to true. Branch metadata responses now include parent_branch_id and merged_from_version_id for better lineage tracking.
Secret dependency management: A new get secret dependencies endpoint (GET /v1/convai/secrets/{secret_id}/dependencies/{resource_type}) returns paginated dependency lookups filtered by resource type (tools, agents, or phone_numbers). The list secrets endpoint now accepts a dependency_limit query parameter to control how many dependencies are previewed per secret, with agents_has_more, tools_has_more, and phone_numbers_has_more flags indicating when additional dependents exist beyond the preview.
New LLM options: Added gemini-3.1-pro-preview, qwen35-35b-a3b, and qwen35-397b-a17b to the list of available LLM providers for agent configuration.
voice_type query parameter on the list voices endpoint now accepts non-community, which returns personal and workspace voices combined while excluding library copies. This provides a convenient filter for teams that want to see only their own voices without community-shared ones.@elevenlabs/client@1.2.0 - Fixed getInputVolume() and getOutputVolume() returning 0 in React Native by adding native volume providers using LiveKit's RMS and multiband FFT processors. getInputByteFrequencyData() and getOutputByteFrequencyData() now return data focused on the human voice range (100-8000 Hz), which is more useful for voice visualization, and on web getInputVolume() and getOutputVolume() are also computed from this range.
@elevenlabs/react@1.1.0 - Fixed startSession errors being swallowed instead of surfaced via onError in ConversationProvider. Previously, when Conversation.startSession() rejected (e.g., "agent not found"), the UI would get stuck in "connecting" with no error feedback.
@elevenlabs/react-native@1.1.0 - Updated to @elevenlabs/client@1.2.0 and @elevenlabs/react@1.1.0 with native volume provider fixes.
@elevenlabs/convai-widget-core@0.11.3 - Fixed transcript message ordering in voice mode where agent responses could appear before user messages.
ElevenAgents Scoped conversation analysis: Evaluation criteria and data collection items can now be scoped to conversation (full transcript) or agent (only the portion where a specific agent was active). Added scope field to PromptEvaluationCriteria, data_collection_scopes to agent platform settings, and a new scoped array of ScopedAnalysisResult on the conversation analysis response. This is particularly useful for multi-agent workflows where each agent should be evaluated independently.Agent test folder management: Tests can now be organized into folders. New endpoints for creating, retrieving, updating, and deleting test folders, plus bulk moving tests between folders.Tool and knowledge base overrides in workflows: Agent workflow node overrides now support tool_ids and knowledge_base fields in PromptAgentAPIModelOverrideConfig, allowing workflow nodes to control which tools and knowledge base documents each sub-agent can access.Response filter hide_all mode: Added hide_all option to ResponseFilterMode, forcing the system to hide all fields of a tool response from the agent.Visited agents in conversation history: The get conversation response now includes a visited_agents array of VisitedAgentRef objects (with agent_id and branch_id), tracking which agents participated in a multi-agent conversation.Multimodal message support in hooks: The useConversationControls hook now exposes sendMultimodalMessage, and the MultimodalMessageInput type is exported from @elevenlabs/client, making it easier to send images and other multimodal content during conversations. Speech to Text Audio duration in responses: The convert speech to text response now includes an audio_duration_secs field, providing the total duration of the transcribed audio without requiring client-side calculation. Voices Recording quality and review status: The get voice response now includes recording_quality (enum: studio, good, ok, poor, bad) and labelling_status (enum: in_review, review_complete) fields, providing visibility into voice quality assessment. SDK Releases JavaScript SDK v2.42.0 - Fern regeneration for the April 7, 2026 API schema, including scoped analysis, test folders, and DTMF input support. Python SDK v2.42.0 - Fern regeneration for the April 7, 2026 API schema, including scoped analysis, test folders, and DTMF input support. Swift SDK v3.1.2 - Fixed ObjC category dispatch for LiveKit delegate methods, resolving potential crashes in Swift-based voice agent integrations. Packages @elevenlabs/client@1.1.1 - Exposed sendMultimodalMessage in the client API and exported the MultimodalMessageInput type for sending images and other multimodal content during conversations.@elevenlabs/client@1.1.2, @elevenlabs/react@1.0.3, @elevenlabs/react-native@1.0.3, @elevenlabs/types@0.9.1 - Fixed Node.js ESM compatibility by adding explicit .js extensions to all relative imports and setting "type": "module" on @elevenlabs/types.@elevenlabs/convai-widget-core@0.11.0 - Added automatic language selection from localStorage history and browser language preferences for the embeddable widget. API
ElevenAgents MCP tool scoping in agent workflows: Agent workflow nodes can now restrict which MCP tools a sub-agent is permitted to call. When tool inheritance is disabled on a node, only the explicitly selected MCP tools are loaded for that sub-agent, giving teams precise control over tool access per workflow step.Conversation file uploads: The create agent and update agent endpoints now support a file_input field on ConversationConfig. When enabled, end users can attach images or PDFs in chat (requires an LLM with multimodal input support). Configurable with enabled (boolean) and max_files_per_conversation (integer).Re-run conversation analysis: New run conversation analysis endpoint (POST /v1/convai/conversations/{conversation_id}/analysis/run) re-evaluates a completed conversation using the agent's current evaluation criteria and data collection settings, without needing a new call.Tool response mocking for tests: Agent simulation tests and test suite invocations now support a tool_mock_config field to control how tool calls are handled during testing. Use MockingStrategy (all, selected, none) to choose which tools are mocked and MockNoMatchBehavior (call_real_tool, raise_error) to set the fallback when no mock matches.Text search sort order: The text search conversations endpoint now accepts a sort_by query parameter with values search_score (default) or created_at, allowing you to control whether results are ordered by relevance or recency.mTLS auth connections: Agent auth connections now support mutual TLS (mtls) as an auth_type, in addition to the existing options. New CreateMTLSAuthRequest and MTLSAuthResponse schemas are available for creating and retrieving mTLS-authenticated connections.Max duration message: Added max_conversation_duration_message field to agent configuration. When set to a non-empty string, the agent will send this message to the user when the maximum conversation duration is reached.Branch and environment in conversation initiation: Added branch_id and environment optional fields to the conversation initiation client data (ConversationInitiationClientDataRequest) and submit batch call request body, enabling routing to specific agent branches and environments. Music Video to music: New POST /v1/music/video-to-music endpoint generates background music from one or more video files. Videos are combined in sequence. Accepts optional description (up to 1,000 characters) and tags (up to 10 style tags such as upbeat or cinematic) to influence the generated track. Speech to Text Transcribe from URL: The convert speech to text endpoint now accepts a source_url parameter (string, optional) for transcribing audio or video from a hosted URL, including YouTube videos, TikTok videos, and other video hosting services. This can be used as an alternative to uploading a file directly. Voices Total count in shared voices list: The list shared voices response now includes a total_count field, making it easier to implement pagination and display result counts. SDK Releases JavaScript SDK v2.41.0 - Added support for the multimodal_message WebSocket event type in ElevenAgents real-time conversations. Includes Fern regeneration for the latest API schema updates.v2.41.1 - Fern regeneration to match the April 1, 2026 API schema. Python SDK v2.41.0 - Fixed audio_interface to be optional in text-only conversation mode, resolving a runtime error when starting a session without audio. Includes Fern regeneration for the latest API schema. Packages This release includes the new v1.0.0 of the client side Agent SDKs. It features major breaking changes to @elevenlabs/client, @elevenlabs/react, and @elevenlabs/react-native. Review the migration guidance below before upgrading. To help upgrade, we released a Skill to help your agents upgrade for you. Install it with npx skills add elevenlabs/packages
You can read more about the v1 release and its improvements on our developer blog. @elevenlabs/client@1.0.0 — Breaking changes:Input and Output classes are no longer exported. Use the InputController and OutputController interfaces from @elevenlabs/client instead.Conversation is no longer a class — it is now a namespace object and a type alias for TextConversation | VoiceConversation. Remove any instanceof Conversation checks and subclasses.The default connectionType is now inferred from the conversation mode: voice conversations use "webrtc" by default, and text-only conversations use "websocket". To keep the previous behavior for voice, pass connectionType: "websocket" explicitly.VoiceConversation.wakeLock is now private. Pass useWakeLock: false in session options to suppress wake lock management.changeInputDevice() and changeOutputDevice() now return Promise instead of Promise or Promise.Replace conversation.input.analyser.getByteFrequencyData(data) with conversation.getInputByteFrequencyData().Replace conversation.input.setMuted(v) with conversation.setMicMuted(v).Replace conversation.output.gain.gain.value = v with conversation.setVolume({ volume: v }).getInputVolume(), getOutputVolume(), getInputByteFrequencyData(), and getOutputByteFrequencyData() now return 0 or an empty Uint8Array instead of throwing when no conversation is active.@elevenlabs/react@1.0.0 — Breaking changes:useConversation now requires a ConversationProvider ancestor. Wrap your component tree in and move options to the provider or to the hook.DeviceFormatConfig and DeviceInputConfig exports are removed. Use FormatConfig and InputDeviceConfig from @elevenlabs/client instead.New granular hooks replace the monolithic useConversation for better render performance: useConversationControls(), useConversationStatus(), useConversationInput(), useConversationMode(), useConversationFeedback(), and useRawConversation(). Each hook subscribes only to the state it needs, preventing unnecessary re-renders.New useConversationClientTool(name, handler) hook for registering client tools that agents can invoke, with automatic cleanup on unmount.Added controlled mute support via isMuted and onMutedChange props on ConversationProvider.@elevenlabs/react-native@1.0.0 — Breaking changes:The previous ElevenLabsProvider and useConversation API have been removed and replaced with re-exports from @elevenlabs/react. Replace ElevenLabsProvider with ConversationProvider and useConversation with the granular hooks (useConversationControls, useConversationStatus, etc.).On React Native, the package now polyfills WebRTC globals, configures the native AudioSession, and registers a platform-specific voice session strategy on import.@elevenlabs/types@0.8.0 - Exports the CALLBACK_KEYS runtime array containing all keys from the Callbacks interface, used internally by the React SDK for callback composition.@elevenlabs/client@0.16.0 - Added the guardrail_triggered server-to-client WebSocket event and the onGuardrailTriggered callback, which fires when the server detects a guardrail violation during a conversation. Also added type discriminants to TextConversation and VoiceConversation to enable discriminated union narrowing, and added startSession overloads that narrow the return type based on the textOnly option.@elevenlabs/react-native@0.6.0 - Added the guardrail_triggered WebSocket event and onGuardrailTriggered callback, consistent with @elevenlabs/client@0.16.0.@elevenlabs/client@1.1.0 - Added client-side support for mocking tool responses in agent conversations, enabling test scenarios that simulate tool call outcomes without invoking real tools.@elevenlabs/types@0.9.0 - Added type definitions for tool response mocking in agent conversations.@elevenlabs/react@1.0.1 - Updated to depend on @elevenlabs/client@1.1.0.@elevenlabs/react-native@1.0.1 - Updated to depend on @elevenlabs/client@1.1.0 and @elevenlabs/react@1.0.1. API
Workspace Basic and Full Seats: Workspaces now support two seat types - Full Seats with unrestricted access to all products, and Basic Seats with full access to ElevenAgents and ElevenAPI and limited ElevenCreative usage. All paid plans include 20 Basic Seats. Enterprise admins can purchase additional Full Seats directly from workspace settings. Learn more.
ElevenAgents Environment Variables API: New environment variables endpoints for managing workspace-level configuration that agents can reference at runtime via {{system_env__}} templating. Supports string, secret, and auth-connection variable types with per-environment value overrides. Endpoints include create, list, get, and update.Auth Connections management: New workspace-level auth connections API for managing authentication credentials used by agent tools and integrations. Supports multiple auth methods including OAuth2 client credentials, JWT, basic auth, bearer tokens, custom headers, and integration-managed OAuth2 authorization code flows. Endpoints include create, list, and delete operations.Knowledge Base URL refresh: New refresh endpoint (POST /v1/convai/knowledge-base/{documentation_id}/refresh) to re-fetch and update content for URL-sourced knowledge base documents. Knowledge base documents also now support auto-sync configuration with enable_auto_sync, auto_remove, and auto_sync_info fields.Guardrail retry with feedback: Custom and content guardrails now support configurable trigger actions with EndCallTriggerAction and RetryTriggerAction options. When set to retry, the agent re-generates its response with injected system feedback up to 3 attempts. Available placeholders include {{trigger_reason}} and {{agent_message}} for contextual retry guidance.Conversation History system variable: Added a new system__conversation_history dynamic variable that provides a lazily-evaluated, JSON-serialized conversation history at runtime. This is useful for passing full conversation context to tools, webhooks, or sub-agent handoffs.Webhook tool content type: Server tools now support a configurable content type for webhook body parameters, allowing you to choose between application/json and application/x-www-form-urlencoded formats. The URL-encoded format is useful for integrating with legacy systems, OAuth token endpoints, and payment processors.WhatsApp outbound messages: Updated the WhatsApp integration with a new outbound message dialog in the dashboard, enabling agents to send outbound messages in addition to calls through the WhatsApp channel.Agent and resource listing filters: The list agents, list knowledge base documents, and list tools endpoints now support a created_by_user_id query parameter (use @me for the current user). The previous show_only_owned_agents and show_only_owned_documents parameters are deprecated.Workflow conditional expressions: Added a new conditional_operator AST node to the workflow expression schema, enabling branching logic within agent workflow definitions. Music Music Marketplace: New Music Marketplace documentation covering the marketplace for licensing AI-generated music, including usage types, creator payouts, and licensing details. SDK Releases Python SDK v2.40.0 - Added environment parameter support for ElevenAgents conversations, enabling environment-specific agent connections. Fern regeneration to match the latest API schema including environment variables, auth connections, knowledge base refresh, and guardrail trigger actions. JavaScript SDK v2.40.0 - Added multimodal_message WebSocket event type for ElevenAgents real-time conversations. Fern regeneration to match the latest API schema including environment variables, auth connections, knowledge base refresh, and guardrail trigger actions. iOS SDK v3.1.1 - Added environment parameter support for environment-specific agent connections. Fixed a visionOS build error by bumping the platform requirement to v2. Packages @elevenlabs/types@0.6.1 - Added multimodal_message WebSocket event type for ElevenAgents real-time conversations.@elevenlabs/client@0.15.2 - Added multimodal_message WebSocket event support.@elevenlabs/react@0.14.3 - Added multimodal_message WebSocket event support.@elevenlabs/convai-widget-core@0.10.4, @elevenlabs/convai-widget-core@0.10.5 - Updated to @elevenlabs/client@0.15.2.@elevenlabs/convai-widget-embed@0.10.4, @elevenlabs/convai-widget-embed@0.10.5 - Updated to @elevenlabs/client@0.15.2. Packages v1.0.0 Release Candidate The first release candidate for v1.0.0 of the ElevenAgents client SDKs is now available. This is a major release with breaking changes that improve the API surface, add granular React hooks for better render performance, and unify the React Native SDK with the React SDK. To try out the release candidate: npm install @elevenlabs/client@next @elevenlabs/react@next @elevenlabs/react-native@next
An elevenlabs:sdk-migration skill is available to help AI coding assistants automatically migrate your codebase to the new APIs. Add it to your Claude Code, Cursor, or Windsurf project to get guided migration support. Key changes in v1.0.0: @elevenlabs/client: Conversation is now a namespace object and type alias for TextConversation | VoiceConversation instead of a class. The Input and Output classes are replaced by InputController and OutputController interfaces, with new convenience methods on the conversation instance (setMicMuted(), setVolume(), getInputByteFrequencyData(), getOutputByteFrequencyData()). changeInputDevice() and changeOutputDevice() now return void.@elevenlabs/react: useConversation now requires a ConversationProvider ancestor. New granular hooks for fine-grained re-rendering: useConversationControls(), useConversationStatus(), useConversationInput(), useConversationMode(), useConversationFeedback(). New useConversationClientTool() hook for dynamically registering client tools from React components with full type safety.@elevenlabs/react-native: Complete API rewrite replacing ElevenLabsProvider and useConversation with ConversationProvider and the same granular hooks from @elevenlabs/react. WebRTC polyfills and native AudioSession configuration are applied automatically on import. See the full release notes and migration guides: @elevenlabs/client@1.0.0-rc.1@elevenlabs/react@1.0.0-rc.1@elevenlabs/react-native@1.0.0-rc.1@elevenlabs/types@0.7.0-rc.0 API
ElevenAgents Users page is now generally available: The list users page, which groups conversations by a user identifier, is now available to all workspaces. This allows you to view all users who have interacted with your agents, their conversation history, and contact details in a unified view.SIP inbound headers as dynamic variables: Custom SIP X- headers from inbound SIP trunking calls are now automatically exposed as dynamic variables in ElevenAgents conversations. Any custom SIP header (e.g., X-Contact-ID, X-Campaign-ID) passed by the caller is available in the agent prompt using {{sip_contact_id}}, {{sip_campaign_id}}, etc. These variables are also visible in the conversation history under the Phone Call tab. Reserved headers such as X-Call-ID and X-Caller-ID continue to map to system__call_sid and system__caller_id and are not overridden.Conversation filtering by tool outcome: The list conversations and text search conversations endpoints now accept tool_names_successful and tool_names_errored query parameters (array of strings) to filter conversations by which tools succeeded or returned errors during the call.User listing improvements: The list users endpoint now supports a sort_by query parameter accepting last_contact_unix_secs (default) or conversation_count, and a branch_id query parameter to filter users by agent branch.Force delete tools: The delete tool endpoint now accepts a force query parameter (boolean, default false). When set to true, the tool is deleted even if it is used by agents, and it is automatically removed from all dependent agents and branches.Conversation embedding retention: The ElevenAgents settings response now includes conversation_embedding_retention_days, which controls how long conversation embeddings are retained (maximum 365 days). A null value uses the system default of 30 days.Content threshold guardrail: Added the ContentThresholdGuardrail schema, which provides a configurable threshold-based guardrail with an is_enabled flag and a threshold value for content moderation. Workspaces Get all workspace groups: New GET /v1/workspace/groups endpoint returns all groups in the workspace, including each group's name, ID, members, permissions, usage limit, and character count.Seat type in bulk workspace invites: The invite multiple users endpoint now accepts an optional seat_type field to specify the seat type (e.g., workspace_member, workspace_admin) for all invited users in a bulk operation.Mobile SSO reliability improvements: Fixed a regression where SSO login on mobile would get stuck on "Authenticating..." after a user logged out and attempted to sign in again. Also fixed workspace switching for mobile SSO users who sign in via SAML or OIDC providers. Music Section duration control: The generate music detailed endpoint now supports respect_sections_durations (boolean), which controls whether the model adheres to the duration specified for each section in the composition plan. ElevenCreative Studio Chapter visual content indicator: Chapter response models now include a has_visual_content boolean field indicating whether the chapter contains visual content.Text shadow and outline styles: ElevenCreative Studio text styling now supports text_shadow and text_outline options via the new StudioTextStyleShadowModel and StudioTextStyleOutlineModel schemas, enabling richer visual text customization within ElevenCreative Studio projects.Media generation clip task type: The PendingClipTask.type enum now includes the media_generation value, expanding clip task categorization to cover media generation workflows. SDK Releases Python SDK v2.39.0 - Added support for the multimodal_message WebSocket event type in ElevenAgents real-time conversations.v2.39.1 - Fern regeneration to match the latest API schema. JavaScript SDK v2.39.0 - Fern regeneration to match the latest API schema. iOS SDK v3.1.0 - Several improvements to the ElevenAgents Swift SDK:Server errors are now surfaced through the onError callback, making error handling more consistent.Added event-based agent state management for cleaner state observation.Software muting is now supported alongside speech detection, enabling more granular audio control.Improved codebase to use Swift Concurrency throughout.Fixed a crash that occurred during startup on iOS release builds.Updated branding to reflect the ElevenAgents rebrand. Packages @elevenlabs/client@0.15.1 - Added audio resampling for output audio when the required sample rate cannot be acquired from the system, improving compatibility across devices.@elevenlabs/react@0.14.2 - Updated to depend on @elevenlabs/client@0.15.1.@elevenlabs/convai-widget-core@0.10.3 - Updated to depend on @elevenlabs/client@0.15.1. API
New Schemas: Environment variable models (ConvAIEnvironmentVariable, ConvAIEnvVarLocator, EnvironmentAuthConnectionLocator), guardrail trigger actions (EndCallTriggerAction, RetryTriggerAction), conditional expressions (ConditionalOperator), auth connection management schemas, and speech-to-text evaluation schemas.
Modified Schemas: MCPServerConfig now supports environment variable references, CustomGuardrailConfig added trigger_action field, Contributor added optional bio and profile_id fields, ASTLLMNode added value_schema (with prompt deprecated), and TelephonyDirection refactored as a shared enum.
ElevenAgents: Users page now generally available with unified conversation history view. Custom SIP X-headers automatically exposed as dynamic variables (e.g., {{sip_contact_id}}). Conversation filtering by tool outcome via tool_names_successful and tool_names_errored query parameters. User listing now supports sort_by (by contact time or conversation count) and branch_id filters. Force delete tools with automatic removal from dependent agents. Conversation embedding retention control via conversation_embedding_retention_days field. New ContentThresholdGuardrail schema.
Workspaces: New endpoint to get all workspace groups with member and permission details. Bulk invite endpoint now supports optional seat_type field. Fixed mobile SSO regressions with stuck authentication and workspace switching.
Music: Generate music detailed endpoint now supports respect_sections_durations to control adherence to per-section durations.
ElevenCreative Studio: Chapters now include has_visual_content boolean field. Text styling now supports text_shadow and text_outline via new schemas. Clip task type enum expanded with media_generation value.
SDK Releases: Python v2.39.0/2.39.1 with WebSocket multimodal event support and schema updates. JavaScript v2.39.0 with schema updates. iOS v3.1.0 with improved error handling, event-based state management, software muting, Swift Concurrency, crash fixes, and rebranding. Client packages updated with audio resampling support.
ElevenAgents New LLM options: Added claude-sonnet-4-6 and gemini-3.1-flash-lite-preview as supported LLM providers for agent conversation configuration.Guardrail execution mode: Custom guardrails now support a configurable execution_mode field with the GuardrailExecutionMode enum, and have separate input and output schema definitions. This allows more precise control over when guardrail logic runs and which message direction it applies to.Guardrail triggered client event: Added guardrail_triggered to the ClientEvent enum, enabling agent workflows and client-side handlers to respond when a guardrail fires during a conversation.Batch calling concurrency: Added target_concurrency_limit field to the submit batch call request body, allowing you to control the target number of concurrent calls for a given batch.Agent testing type filter: The list agent tests endpoint now accepts a types query parameter to filter results by test type. The include_folders query parameter is deprecated in favor of the new types filter.Telephony call configuration: Added telephony_call_config to outbound call request schemas for Twilio and SIP trunk calls, with a default ringing_timeout_secs of 60 seconds.WhatsApp audio message responses: Added enable_audio_message_response to WhatsApp account configuration, enabling agents to send audio messages in addition to text in WhatsApp conversations. ElevenCreative Studio ElevenCreative Studio agent settings: ElevenCreative Studio project models now expose an agent_settings field using StudioAgentSettingsModel, giving agent-connected studio projects a consistent settings surface alongside the new StudioAgentToolSettingsModel. Mobile SAML SSO for iOS and Android: Enterprise customers using SAML-based identity providers can now sign in from the ElevenLabs iOS and Android apps. Speech to Text No verbatim transcription mode: Added no_verbatim as a transcription option on the convert speech to text endpoint, allowing the model to produce cleaned-up output rather than a verbatim transcript. Music SDK CRLF fix: Resolved an issue in the Python and JavaScript SDKs where the generate music detailed endpoint response was not correctly parsed when the server used \r\n\r\n line endings. The parsers now handle both \r\n and \n line endings. Voices Voice captcha font support for non-Latin scripts: Fixed an issue where the instant voice cloning captcha displayed unreadable characters for some non-Latin scripts. Added font support and correct language selection for Hebrew, Thai, Armenian, Georgian, Malayalam, Telugu, and Gurmukhi. The captcha now uses the actual language of the cloned voice rather than defaulting to English. SDK Releases JavaScript SDK v2.38.0 - Fern regeneration to match the latest API schema, including new ElevenAgents fields, updated SMB tool types, and studio agent settings.v2.38.1 - Fixed CRLF parsing for the music detailed endpoint response stream. Python SDK v2.38.0 - Fern regeneration to match the latest API schema, including new ElevenAgents fields, updated SMB tool types, and studio agent settings.v2.38.1 - Fixed CRLF parsing for the music detailed endpoint response stream. Packages @elevenlabs/convai-widget-core@0.10.1 - Fixed a widget crash on Wix sites where Wix security hardening makes addEventListener non-writable.@elevenlabs/convai-widget-core@0.10.2 - Registered missing livekit-client pnpm patch in patchedDependencies.@elevenlabs/convai-widget-embed@0.10.1 - Fixed a widget crash on Wix sites where addEventListener is non-writable.@elevenlabs/convai-widget-embed@0.10.2 - Registered missing livekit-client pnpm patch in patchedDependencies. API
ElevenAgents New widget configuration options: Several new settings are now available for the ElevenAgents conversation widget in the agent dashboard:Collapsible widget (widget.dismissible): Allow users to minimize or dismiss the widget during a conversation.Action indicator (widget.show_agent_status): Display a visual indicator when the agent is actively using tools, with distinct states for working, done, and error. Enabling this setting automatically adds agent_tool_request and agent_tool_response to the agent's client events.Conversation ID display (widget.show_conversation_id): Show the conversation ID to users after a call ends. Defaults to true for both new and existing agents.Audio tag visibility (widget.strip_audio_tags): Hide audio tags from conversation transcripts. Defaults to true for both new and existing agents.Syntax highlighting theme (widget.syntax_highlight_theme): Configure code block highlighting in transcripts. Accepts null (Auto), light, or dark.Folder-aware agent testing: The List agent tests endpoint now supports organizing tests into folders. Added parent_folder_id, include_folders, and sort_mode query parameters for filtered listing. Test creation and update endpoints accept parent_folder_id to assign tests to folders, and test summaries now include entity type, parent folder path, and children count.Workflow say node: Added a new say node type to agent workflows (WorkflowSayNodeModel). This node supports conversation_config, additional_prompt, and tool and knowledge base overrides. The node's message payload uses a discriminated union with two variants: literal (static text via text) and prompt (LLM-generated via prompt).SMB tool configuration: Formalized the SMBToolConfig schema with a required, discriminated params object. Supported operation types are create, list, search, update, and delete, each applicable to SMB entity categories including clients, staff, services, products, and assets.Summary language for agents: Added summary_language field to agent configuration to specify the language for post-conversation summaries.Twilio call recording: Added optional call_recording_enabled field to the Twilio outbound call request body to enable recording of outbound calls.WhatsApp messaging flag: Added enable_messaging flag to WhatsApp account models and update requests to control whether messaging is enabled for a given phone number. Pronunciation Dictionaries Set all rules at once: New Set rules endpoint (POST /v1/pronunciation-dictionaries/{pronunciation_dictionary_id}/set-rules) replaces all existing rules in a pronunciation dictionary in a single call, as an alternative to incrementally adding or removing individual rules.Rule matching options: Added case_sensitive (boolean) and word_boundaries (boolean) fields to pronunciation dictionary rule definitions for more precise control over how rules match text. Music Upload audio: New Upload music endpoint (POST /v1/music/upload) accepts a multipart/form-data request with an audio file. Optionally extracts a composition plan from the uploaded audio and returns a MusicUploadResponse with a song_id.Phonetic name support: Added use_phonetic_names parameter to Generate music, Generate music detailed, and Stream music endpoints.Song ID in responses: Music generation responses now surface the song_id field, making it easier to reference generated songs in subsequent API calls. Audio Native Update project content from URL: New Update content endpoint (POST /v1/audio-native/content) allows updating an AudioNative project by providing a URL. The endpoint extracts the content from the URL and queues it for conversion and auto-publishing. Voices Voice bookmarking: Added bookmarked field to voice update requests and is_bookmarked to voice response objects, enabling users to bookmark voices for easy access. SDK Releases JavaScript SDK v2.37.0 - Added support for surfacing song_id in music generation responses. Updated to include latest API schema changes from Fern regeneration. Python SDK v2.37.0 - Added support for new music generation parameters and surfacing song_id in music generation responses. Updated to include latest API schema changes from Fern regeneration. Packages @elevenlabs/convai-widget-core@0.10.0 - Propagated event_id through transcript and streaming callbacks. Refactored tool status tracking from Map-based to inline transcript entries with a display-transcript utility. Added show-conversation-id config option (boolean, defaults to true) to control visibility of conversation ID in disconnection messages.@elevenlabs/convai-widget-embed@0.10.0 - Propagated event_id through transcript and streaming callbacks. Refactored tool status tracking to inline transcript entries.@elevenlabs/types@0.6.0 - Propagated event_id through transcript and streaming callbacks. API
ElevenAgents OAuth and advanced authentication for MCP servers: MCP servers now support workspace auth connections, enabling OAuth2 Client Credentials, Basic Auth, Bearer Auth, JWT, and custom header authentication. Select an auth connection when creating or editing an MCP server to automatically handle token refresh and authentication headers. See the MCP server documentation for more details.LLM information endpoint: Added a new endpoint to list available LLMs with deprecation status, capabilities, and context limits. This enables clients to programmatically discover which models are available and which are being deprecated. See List Available LLMs for details.Conversation history redaction: Added support for redacting sensitive information from conversation transcripts, audio, and analysis before being stored. Configure specific entity types to redact (such as names, email addresses, etc.) using the new conversation_history_redaction setting in agent privacy configuration. See the docs page for more details.Enhanced guardrails: Introduced two new guardrail types for agents:focus: Helps keep conversations on-topicprompt_injection: Detects and prevents prompt injection attemptsNote: The alignment guardrail has been removedConversation search endpoints: Added two new endpoints for searching conversation messages:Text search - Full-text and fuzzy search over transcript messagesSmart search - Semantic search using embeddingsFile uploads in conversations: Added endpoints to upload and manage files within conversations:Upload file - Upload files to a conversationDelete file - Remove uploaded filesNew embedding model: Added support for qwen3_embedding_4b embedding model in knowledge base RAG indexing. Workspaces Image and video generation permission: Workspace administrators can now control access to image and video generation features. This new permission allows you to restrict which workspace members can use these capabilities. Configure this in your workspace settings under member permissions. Music Workspace sharing: Songs can now be shared within workspaces. The songs resource type has been added to workspace resource sharing endpoints. SDK Releases JavaScript SDK v2.36.0 - Added overloaded convert method signatures to Speech to Text wrapper for improved type safety and ergonomics. Updated SDK to include latest API schema changes including LLM list endpoint, conversation search, and MCP auth connection support. Python SDK v2.36.1 - Added missing music generation parameters including seed, loudness, quality, and guidance_scale to ensure full feature parity with the API.v2.36.0 - Renamed package references from "Conversational AI" to "ElevenAgents" to reflect the product rebrand. Updated SDK to include latest API schema changes including LLM list endpoint, conversation search, and MCP auth connection support. Packages @elevenlabs/convai-widget-core@0.9.0 - Updated widget core with latest features and improvements@elevenlabs/convai-widget-embed@0.9.0 - Updated embeddable widget with latest features and improvements@elevenlabs/react-native@0.5.10 - React Native SDK updates@elevenlabs/types@0.5.0 - Updated TypeScript types package API
ElevenAgents Conversation users endpoint: Added Get conversation users endpoint (GET /v1/convai/users) to list users who have had conversations with your agents. Supports pagination and filtering by agent, time range, and other criteria.Agent versioning: Fetch specific agent configurations by version using the new version_id and branch_id query parameters on the Get agent endpoint. The Update agent endpoint also now accepts a branch_id parameter for branch-specific updates.Search documentation tool: Added search_documentation as a new built-in system tool for RAG (retrieval-augmented generation). Configure multi-source retrieval with MultiSourceConfigJson, SourceConfigJson, and SourceRetrievalConfig schemas. Supports configurable merging strategies via the MergingStrategy enum.MCP tool support: Added mcp as a new tool type alongside webhook, client, and system tools. Configure MCP tools using the new MCPToolConfig schema in your agent tool definitions.Content guardrails: Added content moderation guardrails to GuardrailsV1 with configurable thresholds for different content categories: sexual, violence, harassment, self-harm, profanity, religion/politics, and medical/legal content. Use the new ContentGuardrail and ContentConfig schemas.Expressive mode: Added expressive_mode field (boolean) to agent configuration schemas to automatically prompt your agent to make the most of the new v3 conversational model.Post-dial digits: Phone number transfers now support post_dial_digits for sending DTMF tones after connection. Configurable as static values or dynamic variables.Agent testing types: Agent testing now supports three distinct test types with dedicated schemas: llm (response evaluation), tool (tool-call verification), and simulation (full conversation simulation). Simulation tests include simulation_scenario and simulation_max_turns configuration fields. Pronunciation Dictionaries Rules in API response: The Get pronunciation dictionary endpoint now returns a rules array containing full rule details. Response uses the new GetPronunciationDictionaryWithRulesResponseModel schema with PronunciationDictionaryAliasRuleResponseModel and PronunciationDictionaryPhonemeRuleResponseModel for rule types. Knowledge Base Folder deletion: The Delete knowledge base document endpoint now supports deleting folders in addition to documents. When deleting folders, set force=true to enable recursive deletion of all contained documents and subfolders. SDK Releases Python SDK v2.36.0 - Added conversation users endpoint, agent versioning, search documentation tool, MCP tool support, content guardrails, and agent testing types JavaScript SDK v2.36.0 - Added overloaded convert signatures to speechToText.convert() for improved type inference based on request parameters (access .text, .transcripts, or webhook fields without manual type narrowing), added conversation users endpoint, agent versioning, search documentation tool, MCP tool support, content guardrails, and agent testing types Widget Packages @elevenlabs/convai-widget-core@0.9.0 - Added agent tool usage status display and new status badge for long-running tool calls, fixed emotion tag stripping, fixed rating and feedback submission for signed-url widget embedding@elevenlabs/convai-widget-embed@0.9.0 - Added agent tool usage status display and new status badge for long-running tool calls, fixed emotion tag stripping API
ElevenAgents, ElevenCreative and ElevenAPI We’re moving from a single-product perception (“ElevenLabs”) to a platform-based structure with clearly defined product families: ElevenAgents (Formerly Agents Platform)ElevenCreative (Formerly Creative Platform)ElevenAPI (New, the Developer Platform) You'll already see this reflected in the docs and SDK readmes. Global servers out of beta Global routing is now the default rather than opt-in. Previously the default ElevenLabs API server was located in the United States, with an opt-in beta for routing traffic through the Netherlands or Singapore based servers. As of now global routing is the default, meaning that the server will automatically be chosen based on geographic proximity to optimize latency. The opt-in base URL api-global-preview.elevenlabs.io is now deprecated, please use the default api.elevenlabs.io base URL instead. If you're using the SDKs, this is already the default. Text to Speech TTS Normalizer v3.1: Upgraded the text normalizer to version 3.1, which includes improved accuracy and lower latency for text-to-speech conversion. Agents Platform Custom guardrails: Added support for user-defined output guardrails that allow you to create custom content filtering rules beyond standard moderation. Configure guardrails with a name, prompt instruction (up to 10,000 characters), and choice of evaluation model (gemini-2.5-flash-lite or gemini-2.0-flash). When triggered, the guardrail ends the conversation. See the Create agent API reference for configuration details.WhatsApp outbound messaging: Added Send outbound message endpoint (POST /v1/convai/whatsapp/outbound-message) to initiate conversations via WhatsApp using message templates. Required fields include whatsapp_phone_number_id, whatsapp_user_id, template_name, template_language_code, template_params, and agent_id.Eleven v3 conversational model: Added eleven_v3_conversational to the available TTS models for agents, providing improved voice quality and expressiveness in agent conversations.Suggested audio tags: Added suggested_audio_tags field to TTS configuration for agents using v3 models. Define up to 20 tags (e.g., "happy", "excited") to guide expressive speech generation, with optional descriptions for when each tag should be used.Tool error handling: Added tool_error_handling_mode field to webhook tool configurations with options: auto (default, determines handling based on tool type), summarized (sends LLM-generated summary), passthrough (sends raw error), or hide (does not share error with agent).Dynamic variable sanitization: Added sanitize field (boolean, default false) to DynamicVariableAssignment. When enabled, the assignment value is removed from tool responses and transcripts while still being processed for variable assignment.Turn model selection: Added TurnModel enum with turn_v2 and turn_v3 options for selecting the turn detection model version.Workflow node transfers: Added is_workflow_node_transfer field (boolean, default false) to AgentTransfer schema for identifying transfers within workflow nodes.Transfer branch metadata: Added TransferBranchInfoTrafficSplit and TransferBranchInfoDefaultingToMain schemas for tracking branch routing information in agent transfers.Workflow node transition testing: Added workflow_node_transition assertion type for unit tests with UnitTestWorkflowNodeTransitionEvaluationNodeId schema to validate agent workflow transitions. ElevenCreative Studio Muted tracks endpoint: Added Get project muted tracks endpoint (GET /v1/studio/projects/{project_id}/muted-tracks) that returns a list of chapter IDs with muted tracks in a project. Workspaces Lite member seat type: Added workspace_lite_member to the SeatType enum for workspaces with limited access permissions.Content templates resource: Added content_templates to WorkspaceResourceType enum for sharing content templates within workspaces. User Interface Voice collection scrolling: Fixed an issue preventing mouse wheel and touch scrolling in the voice collection icon picker on macOS. SDK Releases Python SDK v2.35.0 - Added custom guardrails, WhatsApp outbound messaging, tool error handling mode, dynamic variable sanitization, turn model selection, and Eleven v3 conversational model support JavaScript SDK v2.35.0 - Added custom guardrails, WhatsApp outbound messaging, tool error handling mode, dynamic variable sanitization, turn model selection, and Eleven v3 conversational model support React and Client SDKs @elevenlabs/react-native@0.5.10 - Fixed establishing text-only conversations@elevenlabs/react@0.14.0 - Reduced audio chunk length from 250ms to 100ms for lower latency in agent conversations@elevenlabs/client@0.14.0 - Reduced audio chunk length from 250ms to 100ms for lower latency, normalized textOnly option handling between top-level and overrides object@elevenlabs/types@0.5.0 - Added types for audio alignment data support API
Eleven v3 v3 is out of alpha - it's more stable, accurate and has lower latency. Read more about Eleven v3. Text-to-Dialogue WAV output formats: Text-to-Dialogue endpoints now support WAV output formats (wav_8000, wav_16000, wav_22050, wav_24000, wav_32000, wav_44100, wav_48000) in addition to existing MP3, PCM, OPUS, and other formats. WAV formats with 44.1kHz sample rate require a Pro tier subscription or above. Agents Platform Agent branch renaming: You can now rename agent branches using the Update branch endpoint. The new optional name field accepts 1-140 characters.Alignment guardrails: Added AlignmentGuardrail type to GuardrailsV1 schema for enhanced conversation safety controls.Speculative turn configuration: Added speculative_turn field to turn configuration for fine-tuning agent turn-taking behavior.Procedure references: Agent patch requests now support procedure_refs for referencing reusable procedures.Webhook response filtering: Added response_filter_mode and response_filters fields to webhook overrides, with new ResponseFilterMode enum for controlling which response data is passed through.Error details in tool events: Added raw_error_message field to API integration webhook, system, and workflow tool event models for improved debugging.Flexible tool call matching: Testing models now include check_any_tool_matches option to relax tool call matching requirements during agent testing.Secrets pagination: Get workspace secrets endpoint now supports pagination with page_size (max 100) and cursor query parameters, returning next_cursor and has_more in responses. Workspaces Permission clarifications: Workspace group and invite endpoints now document specific permission requirements (group_members_manage for group member operations, WORKSPACE_MEMBERS_INVITE for workspace invitations) instead of requiring workspace administrator status.New permission types: Added group_members_manage and terms_of_service_accept to the PermissionType enum. User Compliance terms visibility: Added show_compliance_terms field to user response model. Metrics ASR provider tracking: Added convai_asr_provider field to metrics for tracking automatic speech recognition provider usage. SDK Releases Python SDK v2.34.0 - Added WAV output formats for Text-to-Dialogue, webhook response filtering, agent branch renaming, secrets pagination, and speculative turn configurationv2.33.1 - Fixed bug with URL streaming in Scribev2.33.0 - Fixed bug with agent initialization and user_id handling, added audio alignment callback for agent conversations JavaScript SDK v2.34.0 - Added WAV output formats for Text-to-Dialogue, webhook response filtering, agent branch renaming, secrets pagination, and speculative turn configuration React and Client SDKs @elevenlabs/client@0.14.0-beta.0 - Reduced audio chunk length from 250ms to 100ms for lower latency in agent conversations@elevenlabs/react@0.14.0-beta.0 - Reduced audio chunk length from 250ms to 100ms for lower latency in agent conversations@elevenlabs/client@0.13.1 - Fixed issue where input audio would not re-establish after microphone permission revocation@elevenlabs/react@0.13.1 - Fixed issue where input audio would not re-establish after microphone permission revocation Widget Packages @elevenlabs/convai-widget-core@0.8.1 - Fixed microphone mute state reset when call ends to prevent UI/audio desync on subsequent calls@elevenlabs/convai-widget-embed@0.8.1 - Fixed microphone mute state reset when call ends@elevenlabs/convai-widget-core@0.8.0 - Fixed styling issue in shadow root@elevenlabs/convai-widget-embed@0.8.0 - Fixed styling issue in shadow root@elevenlabs/convai-widget-core@0.7.0 - Updated Tailwind to v4, added optional dismissable widget parameter, and fixed microphone permission handling@elevenlabs/convai-widget-embed@0.7.0 - Updated Tailwind to v4, added optional dismissable widget parameter API
Agents Platform Agent branching and deployments: Added a complete version control system for agents, enabling teams to create branches, iterate on agent configurations in isolation, and merge changes when ready. New endpoints include POST /v1/convai/agents/{agent_id}/branches for creating branches, POST /v1/convai/agents/{agent_id}/branches/{source_branch_id}/merge for merging, and POST /v1/convai/agents/{agent_id}/deployments for creating deployments. Drafts can also be created and deleted via the new drafts endpoints. See the Branches and Deployments documentation for details.WhatsApp account management: Added PATCH and DELETE endpoints for WhatsApp Business accounts, allowing you to update and remove connected WhatsApp accounts from agents.Conversation agent name: The Get conversation endpoint now returns agent_name in the response for easier identification of which agent handled a conversation.Error type tracking: Added error_type field to conversation event models for improved debugging and error categorization. Knowledge Base Folder management: Added support for organizing knowledge base documents into folders. New endpoints include Create folder for creating folders, Move document for moving single documents, and Bulk move for moving multiple documents at once. Tools Enhanced tools listing: The Get tools endpoint now supports filtering and pagination with new query parameters including search, page_size, types, sort_by, sort_direction, and cursor. Response now includes next_cursor and has_more fields for pagination. Music Song metadata enhancements: Added bpm and time_signature fields to song metadata for richer audio analysis information. ElevenCreative Studio Caption style templates: Added caption_style_template_overrides field to project models, allowing customization of caption styling per template.Video dubbing project type: Added dub_video to the project creation type enum.Publishing metadata: Added last_updated_from_project_unix timestamp to publishing and project metadata. Workspaces Seat type management: Introduced new SeatType enum with seat_type and workspace_seat_type fields, deprecating the previous workspace_permission and workspace_role fields.Workspace analytics permission: Added workspace_analytics_full_read to the PermissionType enum for granular analytics access control. SDK Releases Python SDK v2.32.0 - Added agent branching, deployments, and drafts endpoints, knowledge base folder management, enhanced tools listing with filtering and pagination, and seat type management JavaScript SDK v2.33.0 - Added agent branching, deployments, and drafts endpoints, knowledge base folder management, enhanced tools listing with filtering and pagination, and seat type management API
Agents Platform Agent summaries endpoint: Added GET /v1/convai/agents/summaries endpoint for retrieving lightweight summaries of all agents in your workspace. This is useful for building agent selection interfaces without fetching full agent configurations.Delete batch calls: Added DELETE /v1/convai/batch-calling/{batch_id} endpoint for removing batch call jobs that are no longer needed.Branch filtering for conversations: Added optional branch_id query parameter to conversation endpoints including GET /v1/convai/conversation/get-signed-url, GET /v1/convai/conversation/token, and GET /v1/convai/conversations for filtering conversations by agent version branch.Spelling patience configuration: Added spelling_patience setting to turn configuration with values auto, low, medium, and high. Controls how long the agent waits before assuming the user has finished spelling something out character by character.Custom SIP headers for transfers: Added support for custom SIP headers when transferring calls via REFER. Configure custom_sip_headers arrays on phone number transfer configurations and workflow phone nodes for advanced telephony integrations.WhatsApp accounts on agents: Agent responses now include whatsapp_accounts array for viewing connected WhatsApp Business accounts.Zendesk integration support: Added zendesk_integration to the ConversationInitiationSource enum for conversations initiated through Zendesk. Audio Output Formats Expanded format options: Audio generation endpoints now support additional output formats including WAV family variants, new OPUS bitrate options, alaw_8000 for telephony, and ultra_lossless quality preset. This applies to Text-to-Speech, Text-to-Dialogue, Sound Generation, Music, and Voice Design endpoints. Dubbing Expanded status values: Dubbing project status now includes additional states for more granular tracking of dubbing progress.Source language: The source_language field is now always returned when fetching a dub's metadata. SDK Releases Python SDK v2.31.0 - Added agent summaries endpoint, delete batch call, branch filtering for conversations, spelling patience configuration, and expanded audio output formatsv2.30.0 - Added WhatsApp accounts on agents, Zendesk integration source, custom SIP headers for transfers, and standardized output format schema JavaScript SDK v2.32.0 - Added audio_format parameter support for Scribe WebSocket URI, agent summaries endpoint, delete batch call, and expanded audio output formatsv2.31.0 - Added WhatsApp accounts on agents, Zendesk integration source, custom SIP headers for transfers, and standardized output format schema React and Client SDKs @elevenlabs/react@0.13.0 - Added conversation initiation overrides, audio alignment event support, WebSocket close code exposure on connection errors, and fixed Firefox AudioContext issue with useScribe hook@elevenlabs/client@0.13.0 - Added conversation initiation overrides, audio alignment event support, and improved Scribe cleanup and disconnect handling Widget Packages @elevenlabs/convai-widget-core@0.6.1 - Added sentence spacing for improved readability and fixed multiline display in user message bubbles@elevenlabs/convai-widget-embed@0.6.1 - Added sentence spacing for improved readability and fixed multiline display in user message bubbles@elevenlabs/convai-widget-core@0.6.0 - Improved error wrapping for conversation token fetching and updated React Native support to 0.81@elevenlabs/convai-widget-embed@0.6.0 - Improved error wrapping for conversation token fetching and updated React Native support to 0.81 API
Scribe v2 We launched Scribe v2, the new state of the art transcription model. Learn more about Scribe v2 in the docs. Agents Platform Timezone support for batch call scheduling: You can now select a timezone when scheduling batch calls. The scheduled time is converted to UTC based on your chosen timezone. Your browser's timezone is automatically selected by default, and validation prevents scheduling calls for times that have already passed in the selected timezone. This makes it easier to schedule outbound calls for the right time in your recipients' time zones.Knowledge Base source file URL: Added a new endpoint to retrieve the original source file URL for knowledge base documents, enabling direct access to uploaded files.LLM fallback cascade timeout: Added cascade_timeout_seconds configuration option for agent backup LLM configs, allowing control over how long to wait before cascading to the next LLM. Default is 8 seconds with an allowed range of 2-15 seconds.Soft timeout LLM-generated messages: Added use_llm_generated_message option to soft timeout configuration. When enabled, the agent will generate a contextual message using the LLM instead of using a predefined message when soft timeout triggers.Knowledge Base folder navigation: Knowledge Base document responses now include folder_path field showing the path segments from root to parent folder, making it easier to understand document hierarchy.Conversation filtering by initiation source: The Get Conversations endpoint now supports filtering by conversation_initiation_source query parameter. Dubbing New transcript format endpoint: Added GET /v1/dubbing/{dubbing_id}/transcripts/{language_code}/format/{format_type} endpoint supporting srt, webvtt, and json output formats. The previous GET /v1/dubbing/{dubbing_id}/transcript/{language_code} endpoint is now deprecated.Required filename for dubbed files: Knowledge Base file models now require a filename field. Speech to Text Entity detection: Added entity_detection option to Speech-to-Text requests. Accepts 'all', specific entity type strings, or an array of entity types. Detected entities are returned in a new entities response field using the DetectedEntity schema.Keyterm prompting: Added keyterms array parameter to Speech-to-Text requests for biasing transcription toward specific terms or phrases. SDK Releases Python SDK v2.29.0 - Added entity detection and keyterm prompting for Speech-to-Text, LLM cascade timeout configuration, soft timeout LLM message generation, and batch call timezone supportv2.28.0 - Added agent versioning fields, voice collection IDs, batch call enhancements, and phone number labels JavaScript SDK v2.30.0 - Added entity detection and keyterm prompting for Speech-to-Text, LLM cascade timeout configuration, soft timeout LLM message generation, and batch call timezone supportv2.29.0 - Added agent versioning fields, voice collection IDs, batch call enhancements, and phone number labels MCP Server v0.9.1 - Added Gemini Extension support, fixed path handling for non-absolute output_directory and missing base_path API
Agents Platform Conversation ID in Twilio/SIP webhooks: The conversation_id is now included in webhook payloads when fetching conversation initiation client data for Twilio, SIP, and WhatsApp integrations. This enables real-time monitoring without polling the API to retrieve conversation IDs.Agent versioning fields: Agent response models now include version_id, branch_id, and main_branch_id fields (nullable strings) for tracking agent versions and branches.Conversation version tracking: Added version_id field to conversation models to identify the agent version used for each conversation.Batch call enhancements: The BatchCallRecipientStatus enum now includes dispatched status, and batch call responses include total_calls_finished field with improved defaults for tracking. Voices Collection IDs: Voice models now include a collection_ids field (array of strings, nullable) indicating which collections a voice belongs to.Voice type filter expansion: The GET /v2/voices endpoint now supports saved as a voice_type filter value for retrieving non-default voices that have been added to a collection. SDK Releases Python SDK v2.28.0 - Updated API schema with agent versioning fields, voice collection IDs, batch call enhancements, and phone number labels JavaScript SDK v2.29.0 - Updated API schema with agent versioning fields, voice collection IDs, batch call enhancements, and phone number labels API
Agents Platform Real-time conversation monitoring: Enterprise users can now monitor agent conversations in real-time via WebSocket connection at /v1/convai/conversations/{id}/monitor. Features include cached conversation history, selective event streaming, and control commands (end call, barge-in, human takeover toggle, send messages).Hinglish language support: Added hinglish_mode configuration option for agents. When enabled and the agent's language is Hindi, responses will be in Hinglish (Hindi-English mix).Dynamic variables in voicemail messages: Voicemail detection messages now support dynamic variable substitution, enabling personalized messages when voicemail is detected.Localized widget terms and conditions: Chat widget terms and conditions can now be localized per language, configured through language presets.Widget conversation mode toggle: Added conversation_mode_toggle_enabled option to widget configuration for controlling conversation mode switching.Batch call retry tracking: Added retry_count field to batch call status responses for tracking retry attempts. Text to Speech Quality preset credit costs: Quality preset descriptions now include credit cost information: high (+20%), ultra (+50%), and ultra_lossless (+100%). WhatsApp Integration Simplified phone number configuration: Replaced whatsapp_business_account_id with whatsapp_phone_number_id in batch calling and conversation info schemas for simpler WhatsApp integration. SDK Releases Python SDK v2.27.0 - Fixed Scribe audio format parameter handling and updated API schemav2.26.1 - Extended on-premises agent configuration support JavaScript SDK v2.28.0 - Fixed Scribe audio format parameter handling and updated API schema Packages @elevenlabs/react@0.12.3 - Localized chat terms and conditions and fixed Scribe audio format@elevenlabs/client@0.12.2 - Localized chat terms and conditions and fixed Scribe audio format@elevenlabs/react-native@0.5.6 - Added TTS speed parameter override and fixed startSession infinite loop in useEffect hooks@elevenlabs/react@0.12.2 - Fixed WebSocket closure code, fixed useConversation race condition, added shadow host event dispatching, and expanded language support@elevenlabs/client@0.12.1 - Fixed WebSocket closure code, fixed useConversation race condition, added shadow host event dispatching, and expanded language support Android SDK v0.7.1 - Fixed agent_tool_request event handling and corrected expects_response default value API
Agents Platform Twilio call registration: Added new endpoint to register Twilio calls and receive TwiML response for agent conversations. Music Generation Word timestamps: Added word-level timestamps to music generation with detailed responses. Enable with the with_timestamps parameter.Fine-tuning support: Added finetune_id parameter to music generation endpoints for using custom music fine-tunes.C2PA content signing: Added sign_with_c2pa option to music generation requests for content authenticity and provenance. Voices Voice settings expansion: Added voice_stability, voice_similarity, and voice_style parameters to voice endpoints for more granular control.Pagination improvements: Clarified pagination behavior for Get all voices v2 endpoint with better documentation of next_page_token, has_more, and total_count fields. ElevenCreative Studio Voice settings override: Added voice_settings parameter to project creation for per-project voice configuration. Webhook Tools Custom request headers: Added request_headers support to Webhook tool configuration for custom authentication and metadata. Billing Schema improvements: Introduced BillingPeriod and CharacterRefreshPeriod enums for better type safety in subscription models. Knowledge Base RAG query rewriting: Added query_rewrite_prompt_override to RAG configuration for customizing query rewriting behavior. SDK Releases JavaScript SDK v2.27.0 - Updated API schema with latest changes including Twilio registration endpoint and music word timestampsv2.26.0 - Added previous_text event support to Scribe and updated event types Python SDK v2.26.0 - Fixed websocket disconnection code for user-triggered closures and updated API schemav2.25.0 - Added on-premises agent configuration support, previous_text event support to Scribe, and improved CI reliability Packages @elevenlabs/react@0.12.1 - Fixed bug with committed transcripts in React components@elevenlabs/agents-cli@0.6.2 - Updated React version@elevenlabs/convai-widget-embed@0.6.0-beta.5 - Improved scroll lock stability in agent widget@elevenlabs/convai-widget-embed@0.5.4 - Fixed auto-scroll behavior, added audioSessionConfiguration to ElevenLabsProvider, and added attributes for worklet scripts Android SDK v0.7.0 - Added sendToolResult function for client tool support iOS SDK v3.0.0 - Major release with breaking changes including onDisconnect now receives disconnect reason, added .thinking agent state, updated LiveKit to 2.10.0+, removed AsyncAlgorithms dependency, and added Swift 5.9+ support (previously required Swift 6.0). Includes SDK hardening, improved error handling, alignment data fixes, and agent response metadata support ElevenLabs CLI @elevenlabs/cli@0.3.2 - Updated React version@elevenlabs/cli@0.3.1 - Fixed SDK dependencies to support recent features API
Agents Platform New LLM support: Extended LLM options with gemini-3-pro-preview model.Out-of-band DTMF: Added use_out_of_band_dtmf flag to PlayDTMFToolConfig for improved DTMF tone handling in telephony integrations.Validation improvements: Reduced maximum items for agent test submission from 200 to 100 for both ResubmitTestsRequestModel.test_run_ids and RunAgentTestsRequestModel.tests to improve performance and reliability.Live analytics: Added new analytics endpoint to retrieve real-time count of active conversations.Custom LLM API types: Added api_type field to CustomLLM schema with enum CustomLLMAPIType supporting chat_completions and responses options for flexible LLM integration.Conversation filtering: Enhanced conversation filtering with support for feedback ratings and comments. Dubbing Speaker management: Added ability to create new speakers for dubbing resources and migrate segments between speakers.Speaker updates: Added speaker_name field support when updating dubbing speakers.Transcript defaults: Relaxed transcript schema requirements with defaults for text, word_type, and speaker_id fields, and removed some required field constraints for easier integration.Language code support: Clarified that source_lang and target_lang fields expect ISO 639-1/3 codes. ElevenCreative Studio Image asset support: Added ProjectImageResponseModel schema for image assets in projects.Project assets: ProjectResponseModel.assets now includes ProjectImageResponseModel for better asset management.Base voices: Added new ProjectResponseModel.base_voices field to project responses.Chapter voice IDs: Added voice_ids field to chapter response models. Workspaces Webhook management: Added comprehensive webhook support with endpoints to create, update, and delete workspace webhooks for better integration capabilities.Extended billing periods: Expanded billing period options to include 3_month_period and 6_month_period.Conversation warnings: Added optional warnings array to conversation-related response models. Music Enhanced prompts: Refined music prompt descriptions to include "musical directions" for more precise music generation guidance. SDKs JavaScript SDK v2.25.1 - Fixed PCM binary parsing for Music SDK.v2.25.0 - Updated SDK to support latest API schema changes including new dubbing endpoints, webhook management, and agent platform improvements. Python SDK v2.24.0 - Updated SDK to support latest API schema changes including new dubbing endpoints, webhook management, and agent platform improvements. React @elevenlabs/react@0.12.0 - Fixed participant disconnect handling, added all Scribe event types, and improved iOS device ID handling.@elevenlabs/react@0.11.3 - Added support for agent tool requests, enabling better integration with Agents Platform tools.@elevenlabs/react@0.11.2 - Build improvements and version updates. Client @elevenlabs/client@0.12.0 - Fixed participant disconnect handling, added all Scribe event types, and improved iOS device ID handling.@elevenlabs/client@0.11.3 - Added support for agent tool requests, enabling better integration with Agents Platform tools.@elevenlabs/client@0.11.2 - Build improvements and version updates.@elevenlabs/client@0.11.1 - Fixed LiveKit URL handling to respect custom LiveKit URLs. React Native @elevenlabs/react-native@0.5.5 - Fixed participant disconnect handling to properly clean up connections when participants leave.@elevenlabs/react-native@0.5.4 - Fixed workspace resolution issue.@elevenlabs/react-native@0.5.3 - Stabilized provider to prevent app reload during calls, added widget markdown renderer, fixed empty stream message handling, and updated Vite dependencies. Types @elevenlabs/types@0.4.0 - Added all Scribe event types for comprehensive speech-to-text event handling.@elevenlabs/types@0.3.1 - Added types provenance for improved package security and integrity. Swift SDK v3.0.0 - Major release with breaking changes including enhanced disconnect handling with reason parameter, new .thinking agent state, LiveKit 2.10.0+ support, Swift 5.9+ compatibility (down from 6.0 requirement), agent response metadata support, and improved error handling with audio pipeline control. API