> 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. ### 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](https://github.com/elevenlabs/elevenlabs-python/releases/tag/v2.31.0) - Added agent summaries endpoint, delete batch call, branch filtering for conversations, spelling patience configuration, and expanded audio output formats - [v2.30.0](https://github.com/elevenlabs/elevenlabs-python/releases/tag/v2.30.0) - Added WhatsApp accounts on agents, Zendesk integration source, custom SIP headers for transfers, and standardized output format schema #### JavaScript SDK - [v2.32.0](https://github.com/elevenlabs/elevenlabs-js/releases/tag/v2.32.0) - Added `audio_format` parameter support for Scribe WebSocket URI, agent summaries endpoint, delete batch call, and expanded audio output formats - [v2.31.0](https://github.com/elevenlabs/elevenlabs-js/releases/tag/v2.31.0) - 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](https://github.com/elevenlabs/packages/releases/tag/@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](https://github.com/elevenlabs/packages/releases/tag/@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](https://github.com/elevenlabs/packages/releases/tag/@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](https://github.com/elevenlabs/packages/releases/tag/@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](https://github.com/elevenlabs/packages/releases/tag/@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](https://github.com/elevenlabs/packages/releases/tag/@elevenlabs/convai-widget-embed@0.6.0) - Improved error wrapping for conversation token fetching and updated React Native support to 0.81 ### API ## New Endpoints - [Get agent summaries](/docs/api-reference/agents/list) - `GET /v1/convai/agents/summaries` - Retrieve lightweight summaries of all agents - [Delete batch call](/docs/api-reference/batch-calling/delete) - `DELETE /v1/convai/batch-calling/{batch_id}` - Remove a batch call job ## Updated Endpoints ### Agents Platform - [Get signed URL](/docs/api-reference/conversations/get-signed-url), [Get conversation token](/docs/api-reference/conversations/get-webrtc-token), [Get conversations](/docs/api-reference/conversations/get-conversations) - Added `branch_id` (string, optional) query parameter for filtering by agent version branch - [Create agent](/docs/api-reference/agents/create), [Update agent](/docs/api-reference/agents/update), [Get agent](/docs/api-reference/agents/get) - Added `spelling_patience` (enum: `auto`, `low`, `medium`, `high`) to turn configuration - Added `whatsapp_accounts` (array) to agent response model - [Simulate conversation](/docs/api-reference/agents/simulate-conversation), [Simulate conversation stream](/docs/api-reference/agents/simulate-conversation-stream) - Request schema updated (breaking change) - [Get conversation](/docs/api-reference/conversations/get) - Removed `initiation_trigger` from metadata (breaking change) ### Voice Management - [Get voices](/docs/api-reference/voices/get-all), [Get voice](/docs/api-reference/voices/get), [Add voice](/docs/api-reference/voices/ivc/create), [Edit voice](/docs/api-reference/voices/update) - Refined `labels` property to documented keys (language, accent, gender, age) with examples ### Audio Generation - [Text to Speech](/docs/api-reference/text-to-speech/convert), [Text to Dialogue](/docs/api-reference/text-to-dialogue/convert), [Sound Generation](/docs/api-reference/text-to-sound-effects/convert), [Music](/docs/api-reference/music/compose) - Expanded `output_format` enum with WAV variants, additional OPUS bitrates, `alaw_8000`, and reordered PCM options - Added `ultra_lossless` to `quality_preset` options ### Speech to Text - [Transcribe speech](/docs/api-reference/speech-to-text/convert) - Added explicit `scribe_v1` and `scribe_v2` enum values for `model_id` ### Dubbing - [Get dubbing project](/docs/api-reference/dubbing/get) - Expanded `status` enum with additional progress states - Added `source_language` (string, required) to dubbing models ### Knowledge Base - [Create knowledge base document](/docs/api-reference/knowledge-base/create-from-url), [Create from file](/docs/api-reference/knowledge-base/create-from-file), [Create from text](/docs/api-reference/knowledge-base/create-from-text) - Added `folder_path` to response model ## Schema Changes ### New Schemas - `CustomSIPHeader` - Configuration for custom SIP headers on call transfers - `SpellingPatience` - Enum for spelling patience settings (`auto`, `low`, `medium`, `high`) - `AllowedOutputFormats` - Centralized enum for audio output format options ### Modified Schemas - `ConversationInitiationSource` - Added `zendesk_integration` enum value - `PermissionType` - Centralized permission enum with new permissions including voice library publishing and user API key creation - `PhoneNumberTransfer` - Added `custom_sip_headers` array - `TurnConfig` - Added `spelling_patience` field > 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.