> 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 - **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](https://github.com/elevenlabs/elevenlabs-python/releases/tag/v2.27.0) - Fixed Scribe audio format parameter handling and updated API schema - [v2.26.1](https://github.com/elevenlabs/elevenlabs-python/releases/tag/v2.26.1) - Extended on-premises agent configuration support #### JavaScript SDK - [v2.28.0](https://github.com/elevenlabs/elevenlabs-js/releases/tag/v2.28.0) - Fixed Scribe audio format parameter handling and updated API schema #### Packages - [@elevenlabs/react@0.12.3](https://github.com/elevenlabs/packages/releases/tag/@elevenlabs/react@0.12.3) - Localized chat terms and conditions and fixed Scribe audio format - [@elevenlabs/client@0.12.2](https://github.com/elevenlabs/packages/releases/tag/@elevenlabs/client@0.12.2) - Localized chat terms and conditions and fixed Scribe audio format - [@elevenlabs/react-native@0.5.6](https://github.com/elevenlabs/packages/releases/tag/@elevenlabs/react-native@0.5.6) - Added TTS speed parameter override and fixed `startSession` infinite loop in useEffect hooks - [@elevenlabs/react@0.12.2](https://github.com/elevenlabs/packages/releases/tag/@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](https://github.com/elevenlabs/packages/releases/tag/@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](https://github.com/elevenlabs/elevenlabs-android/releases/tag/v0.7.1) - Fixed `agent_tool_request` event handling and corrected `expects_response` default value ### API ## New Endpoints - [Get knowledge base summaries](/docs/api-reference/knowledge-base/get-summaries) - Batch fetch document summaries by IDs - [Compute RAG indexes in batch](/docs/api-reference/knowledge-base/compute-rag-index-batch) - Bulk create or retrieve RAG indexes ## Updated Endpoints ### Knowledge Base - [List knowledge base documents](/docs/api-reference/knowledge-base/list) - Added `parent_folder_id` query parameter (string) for filtering by parent folder - Added `ancestor_folder_id` query parameter (string) for filtering by ancestor folder - Added `folders_first` query parameter (boolean) for sorting folders before documents - Document response schemas - Added `folder` document type - Added `folder_parent_id` field (string, optional) - Added `folder_path` field (string, optional) - Added `children_count` field (integer, for folders) - Added `GetKnowledgeBaseFolderResponseModel` schema - Added `GetKnowledgeBaseSummaryFolderResponseModel` schema - RAG index endpoints - Added `cannot_index_folder` status to `RAGIndexStatus` enum - Added batch request/response models for RAG index operations ### Agents Platform - [Create agent](/docs/api-reference/agents/create), [Update agent](/docs/api-reference/agents/update), [Get agent](/docs/api-reference/agents/get) - Added `hinglish_mode` (boolean, default `false`) to agent configuration - Added `hinglish_mode` to workflow override schemas (nullable boolean) - Widget configuration endpoints - Added `conversation_mode_toggle_enabled` (boolean, default `false`) to widget settings - Batch calling endpoints - Added `retry_count` (integer, default `0`) to batch call response models - Conversation token model - Added `token_requester_user_id` (string, nullable) for identifying token requester ### WhatsApp Integration - [Submit batch calling](/docs/api-reference/batch-calling/create) - Replaced `whatsapp_business_account_id` with `whatsapp_phone_number_id` (string, nullable, optional) - Conversation info schemas - Replaced `whatsapp_business_account_id` with `whatsapp_phone_number_id` in `WhatsAppConversationInfo` ### Text to Speech - All TTS endpoints with quality preset - Updated `quality_preset` descriptions to include credit cost percentages ### Workspaces - Resource type enum - Added `convai_agent_drafts` to `WorkspaceResourceType` enum > 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.