Music v2 composition plans; InteractionBudget enum drops async

Introducing Music v2

Music v2 is now available via the ElevenLabs API. Set model_id to music_v2 on Generate music, Stream music, Generate music detailed and Upload music to use the new model. Music v2 introduces chunk-based composition plans built from GenerationChunk and AudioRefChunk segments, giving you finer control over structure, pacing and arrangement than the prompt-based music_v1 flow.

Use music_v2 composition plans on generation and upload requests, or generate a plan first via the composition-plan endpoint. Request and response bodies accept either v1 or v2 plan shapes, so you can migrate endpoint by endpoint. MusicPrompt remains available for music_v1 only.

• Upload timestamps: Upload music accepts optional with_timestamps; responses may include words_timestamps.

ElevenAgents

• Run conversation evaluation: Added Run conversation evaluation endpoint (POST /v1/convai/conversations/{conversation_id}/analysis/evaluations/run) to rerun a single evaluation criterion against a completed conversation using RunConversationEvaluationsRequest.
• Workflow entry behavior: Workflow override-agent nodes add optional entry_behavior (generate_immediately, wait_for_user, auto) to control whether the sub-agent speaks first or waits for user input.
• End procedure system tool: Added end_procedure system tool configuration with matching error statuses. The start_procedure tool adds already_active to its error statuses.
• Transfer TTS overrides: AgentTransfer, workflow standalone agent nodes and successful transfer_to_agent tool results add optional preserve_client_tts_overrides (boolean) to keep client-side TTS overrides after a transfer.
• Interaction budget enum: InteractionBudget removes async and adds 5_minutes, 10_minutes and 1_hour. Update any configs or SDK enums that still reference async.
• Custom guardrail model selection: Custom guardrail configuration adds optional model with Gemini, Claude and GPT variants. Guardrail config also adds optional history_message_count (integer).
• Phone number list filters: List phone numbers adds optional provider, agent_id and branch_id query parameters to filter imported numbers.
• WhatsApp account filtering: List WhatsApp accounts adds optional agent_id query parameter to filter accounts by assigned agent.
• Topic time range filters: Get agent conversation topics adds optional from_unix_secs and to_unix_secs query parameters to bound topic discovery results.
• SIP codec configuration: Outbound SIP trunk request and response models add optional enabled_codecs (MediaCodec enum).
• Memory tool types: Added LoadableMemoryEntry and LoadMemoryEntryToolErrorStatus schemas for memory-tool error handling.
• Agent test batch limits: Agent test attach, run and resubmit request schemas raise maximum attached tests from 1000 to 5000.
• Phoneme tag support: Agent TTS settings add optional enable_phoneme_tags (boolean) for opt-in V3 SSML phoneme handling.
• Array schema omit overrides: Array JSON schema properties add optional is_omitted (mutually exclusive with other value sources). ConstantSchemaOverride can use array constant values.
• Transfer error context: Transfer-to-number error payloads can include optional agent_message (string).

Workspaces

• Service account API key updates: Update service account API key no longer requires a request body. Edit fields support partial updates via no_update and nullable name, including permissions and character_limit.
• Usage timezone bucketing: Workspace usage-by-product-over-time requests add optional time_zone (IANA timezone string) with clarified interval_seconds bucket rules.
• History source filter: History list and detail source filters add Flows.

ElevenCreative Studio

• Project voice references: Project models, chapter TTS nodes, voice lists and voice statistics shift to project_voice_ref_id as the canonical voice field. Former voice_id fields remain on responses as deprecated, read-only mirrors for compatibility.

Speech to Text

• Speaker library diarization: Convert speech to text adds optional use_speaker_library (boolean, default false) for batch transcription diarization.

Voices

• Shared voice sorting: List shared voicessort query parameter gains an explicit enum, created_date default and updated description.

SDK Releases

JavaScript SDK

• v2.53.0 - Regenerated from the latest OpenAPI schema with conversation evaluation rerun support, music v2 composition-plan unions, workflow entry_behavior, phone number and WhatsApp list filters, topic time-range parameters, alerting schema updates, studio project_voice_ref_id fields, and expanded agent test batch limits.

Python SDK

• v2.53.0 - Regenerated from the latest OpenAPI schema with conversation evaluation rerun support, music v2 composition plans, workflow entry behavior and end-procedure tools, telephony filter parameters, alerting and service-account partial-update models, and studio voice reference fields.

Packages

• @elevenlabs/client@1.11.0 - Added @elevenlabs/client/internal/unity sub-path export for the Unity SDK WebGL bridge, exposing MediaDeviceInput, MediaDeviceOutput, connection attach helpers and WebRTC adapter types.
• @elevenlabs/client@1.11.1, @elevenlabs/react@1.6.7, @elevenlabs/react-native@1.2.7, @elevenlabs/convai-widget-core@0.14.2 and @elevenlabs/convai-widget-embed@0.14.2 - Dependency alignment to @elevenlabs/client@1.11.1 and @elevenlabs/types@0.14.1.
• @elevenlabs/types@0.14.1 - Added "license": "MIT" to package.json for license-checker compatibility.

iOS SDK

• v3.2.1 - Added Singapore data residency support and enabled singlePeerConnection for WebRTC sessions.

API