> This is a page from the ElevenLabs documentation. For a complete page index, fetch https://elevenlabs.io/docs/llms.txt. For the full documentation in a single file, fetch https://elevenlabs.io/docs/llms-full.txt.
### Introducing Speech Engine
ElevenLabs Speech Engine adds real-time voice to your own chat agent or LLM. ElevenLabs handles speech-to-text, turn-taking, text-to-speech and browser playback while your server owns the agent logic and streams response text over a Speech Engine WebSocket. Use it when you want voice on a custom runtime rather than a fully hosted ElevenAgents configuration.
Build a voice-enabled agent with the Speech Engine SDK in minutes.
Guidance for AI coding assistants integrating Speech Engine.
Create, update and manage Speech Engine resources over the REST API.
### ElevenAgents
- **Text behavior overrides**: Added `text_behavior_overrides`, a per-`ConversationInitiationSource` map of `BehaviorOverride` objects with optional `verbosity`, `output_format` and `interaction_budget` fields for channel-specific agent behavior.
- **Integration sources**: Added Intercom, Telegram and Freshdesk.
- **OTLP conversation traces**: [Get conversation details](/docs/api-reference/conversations/get) now accepts an optional `format` query parameter. Set `format=otlp_traces` to return OTLP-compatible trace data alongside the standard conversation payload.
- **ASR keyword overrides**: Added `ASRConversationalConfigOverride` and `ASRConversationalConfigOverrideConfig` schemas with optional `keywords` arrays, wired into conversation config client override models.
- **Webhook auth metadata**: Webhook tool configuration schemas now expose optional `auth_resolved_params` (string array) documenting URL placeholders resolved from the auth connection.
### Music
- **Generation mode**: Added `MusicGenerationMode` (`track`, `loop`, `ambience`) and an optional `generation_mode` field on music prompt request bodies.
- **Video to music model**: [Video to music](/docs/api-reference/music/video-to-music) (`POST /v1/music/video-to-music`) now accepts optional `model_id` (string, default `music_v1`).
### ElevenCreative Studio
- **Conversion credits**: Chapter and voice conversion statistics response models now include optional `credits_needed_to_convert` (integer) indicating credits required before conversion.
### Workspaces
- **Resource types**: Added `studio_projects` to `WorkspaceResourceType`.
### SDK Releases
#### Python SDK
- [v2.50.0](https://github.com/elevenlabs/elevenlabs-python/releases/tag/v2.50.0) - Regenerated the SDK for the May 25, 2026 API schema.
- [v2.49.1](https://github.com/elevenlabs/elevenlabs-python/releases/tag/v2.49.1) - Updated Speech Engine API calls to return the full response object.
- [v2.49.0](https://github.com/elevenlabs/elevenlabs-python/releases/tag/v2.49.0) - Regenerated the SDK for the May 18–25, 2026 API schema, including ElevenAgents text behavior overrides, music `generation_mode`, and workspace `studio_projects`.
#### JavaScript SDK
- [v2.50.0](https://github.com/elevenlabs/elevenlabs-js/releases/tag/v2.50.0) - Added missing Music API methods and tests, and regenerated the SDK for the May 25, 2026 API schema.
- [v2.49.1](https://github.com/elevenlabs/elevenlabs-js/releases/tag/v2.49.1) - Updated Speech Engine API calls to return the full response object.
- [v2.49.0](https://github.com/elevenlabs/elevenlabs-js/releases/tag/v2.49.0) - Regenerated the SDK for the May 18–25, 2026 API schema, including ElevenAgents text behavior overrides, music `generation_mode`, and workspace `studio_projects`.
#### Packages
- [@elevenlabs/client@1.8.1](https://github.com/elevenlabs/packages/releases/tag/%40elevenlabs%2Fclient%401.8.1) - Fixed iOS Safari dropping the first agent message on WebSocket voice sessions by unlocking an `AudioContext` on the first user gesture and priming the playback graph after the audio worklet loads.
- [@elevenlabs/convai-widget-core@0.12.8](https://github.com/elevenlabs/packages/releases/tag/%40elevenlabs%2Fconvai-widget-core%400.12.8) and [@elevenlabs/convai-widget-embed@0.12.8](https://github.com/elevenlabs/packages/releases/tag/%40elevenlabs%2Fconvai-widget-embed%400.12.8) - Style emotion and audio tags in voice transcripts when `strip_audio_tags` is off, and treat null top-level `terms_html` or `terms_text` as a kill switch for the terms and conditions modal.
- [@elevenlabs/convai-widget-core@0.12.7](https://github.com/elevenlabs/packages/releases/tag/%40elevenlabs%2Fconvai-widget-core%400.12.7) and [@elevenlabs/convai-widget-embed@0.12.7](https://github.com/elevenlabs/packages/releases/tag/%40elevenlabs%2Fconvai-widget-embed%400.12.7) - Updated widget dependencies to `@elevenlabs/client@1.8.1`.
### API
## Updated Endpoints and Schemas
### ElevenAgents
- [Get conversation details](/docs/api-reference/conversations/get) - `GET /v1/convai/conversations/{conversation_id}`
- Added optional `format` query parameter; `otlp_traces` returns OTLP-compatible trace data
- Agent configuration schemas
- Added `text_behavior_overrides` map keyed by `ConversationInitiationSource` with `BehaviorOverride` values (`verbosity`, `output_format`, `interaction_budget`)
- `ConversationInitiationSource` enum
- Added `intercom_integration`, `telegram_integration` and `freshdesk_integration`
- ASR override schemas
- Added `ASRConversationalConfigOverride` and `ASRConversationalConfigOverrideConfig` with optional `keywords` (array of strings)
- Webhook tool schemas
- Added optional `auth_resolved_params` (string array) on webhook configuration models
### Music
- [Video to music](/docs/api-reference/music/video-to-music) - `POST /v1/music/video-to-music`
- Added optional `model_id` (string, default `music_v1`)
- Music prompt request schemas
- Added optional `generation_mode` referencing `MusicGenerationMode` (`track`, `loop`, `ambience`)
### ElevenCreative Studio
- Chapter and voice conversion statistics schemas
- Added optional `credits_needed_to_convert` (integer)
### Workspaces
- `WorkspaceResourceType` enum
- Added `studio_projects`
> ElevenLabs provides APIs and SDKs for text to speech, voice cloning, speech to text, sound effects, voice isolator, voice changer, and conversational AI agents. Build voice-enabled applications with lifelike audio generation.