Music output quality bump; per-agent topic discovery; branch rebase API

ElevenAgents

• Branch rebase: Added POST /v1/convai/agents/{agent_id}/branches/{branch_id}/rebase to rebase a branch onto the latest main while preserving branch-specific changes. Agent version parent models add optional rebased_from_version_id (string) to track the source version after a rebase.
• Conversation product filtering: List conversations and Text search conversation messages add optional conversation_product_type query parameter (agents | speech_engine) to filter results by product. Conversation models introduce ConversationProduct for this distinction.
• Conversation termination filtering: List conversations adds optional termination_reasons query parameter (array of strings) to filter conversations by how they ended.
• Per-agent topic discovery: Create agent and Update agent platform settings add optional topic_discovery (TopicDiscoverySettings) for per-agent topic discovery configuration.
• Background sound configuration: Agent platform and conversation configuration models add optional background_sound (BackgroundSoundConfig) for ambient audio during conversations.
• Turn interruption ignore terms: Turn configuration schemas add optional interruption_ignore_terms (array of strings) to suppress turn detection on specific phrases.
• Soft timeout filler randomization: Soft timeout configuration adds optional randomize_fillers (boolean) to shuffle filler messages across soft timeouts. Soft timeout message and LLM prompt override fields now support dynamic variables.
• Transcript user identifiers: Transcript message models add optional user_identifier (string) on user-authored messages.
• Simulation success conditions: Agent simulation test schemas add optional success_conditions (array, up to 30 items). The legacy success_condition field is deprecated in favor of the array form.
• Agent test repeat limit: Run tests on the agent raises the maximum repeat_count from 20 to 50.
• Tool schema dynamic allowed values: ElevenAgents tool JSON schema properties add optional allowed_values_dynamic_variable (string) for server-verified LLM value picks sourced from dynamic variables.
• Widget signed URL docs: Get widget updates conversation_signature documentation to reference /v1/convai/conversation/get_signed_url.

Music

• Higher-quality output formats: Generate music, Generate music detailed and Stream music add mp3_48000_240 and mp3_48000_320 to supported output_format values. When output_format is auto, v2 models now default to mp3_48000_192 instead of mp3_48000_128.
• Section duration flag clarification: respect_sections_durations applies only with composition_plan on music_v1. On music_v2, section durations are always enforced and this flag is ignored.
• Composition plan schema split: Music request composition_plan uses a oneOf union of MusicPrompt and CompositionPlan. The former is used for music_v1 composition plans and the latter for music_v2.

Dubbing

• Project list filters: List dubs adds optional dubbing_statuses, dubbing_models, target_language_codes and creation_sources array query parameters for filtered listing. The order_by parameter now accepts name in addition to created_at.

Workspaces

• Lock and disable reasons: Workspace and API key models add LockReason and optional disable_reason fields. Workspace group settings add optional scim_frozen (boolean) for SCIM-managed freeze state.

ElevenCreative Studio

• Caption animations: Studio caption enter and exit animation enums add pop, slide_up and slide_down.

SDK Releases

JavaScript SDK

• v2.54.0 - Regenerated from the latest OpenAPI schema with branch rebase client support, conversation list and text-search conversation_product_type and termination_reasons filters, dubbing list multi-value filters, music-specific output_format types, topic discovery settings, and removal of coaching-related exported types.
• v2.53.1 - Restored optional values in DynamicVariablesConfig records that were incorrectly narrowed in v2.53.0.

Python SDK

• v2.54.0 - Regenerated from the latest OpenAPI schema with branch rebase client support, conversation list and text-search filters, dubbing list multi-value filters, music output format updates, topic discovery settings, and removal of coaching-related exported types. ElevenLabs and AsyncElevenLabs now accept headers and follow_redirects passthrough to the base client.

Packages

• @elevenlabs/client@1.12.0 - Added overrides.asr.keywords support on the browser client so per-conversation ASR keyword biasing can be sent via conversation_initiation_client_data.
• @elevenlabs/react@1.7.0 - Exposed includeLanguageDetection for realtime Scribe sessions, including React useScribe support for requesting and reading detected language metadata.
• @elevenlabs/react-native@1.2.9, @elevenlabs/types@0.15.0, @elevenlabs/convai-widget-core@0.14.4 and @elevenlabs/convai-widget-embed@0.14.4 - Dependency alignment to @elevenlabs/client@1.12.0 and @elevenlabs/types@0.15.0.
• @elevenlabs/client@1.12.1 - Exposed the file upload helper from the internal Unity entrypoint.
• @elevenlabs/react@1.7.1, @elevenlabs/react-native@1.2.10, @elevenlabs/convai-widget-core@0.14.5 and @elevenlabs/convai-widget-embed@0.14.5 - Dependency alignment to @elevenlabs/client@1.12.1.

MCP Server

• v0.10.0 - Added Music v2 model and endpoints, MCP tool annotations for all 24 tools, Python 3.14 support, Singapore data residency, EU/IN residency shorthand aliases, graceful shutdown handling for client disconnections, and fixes for voice preview creation and output directory path resolution.

API