May 13, 2026 | ElevenLabs Documentation

ElevenAgents

SIP logs: SIP signaling logs are now available for SIP trunk calls in conversation history and phone number settings. Logs include the SIP call ID, phone numbers, addresses, transport, message direction, raw messages and errors to help debug call setup and routing issues.
Knowledge base document updates: New API to list indexed (RAG) chunks for a document. Documents can also be edited in place: rename the item and, for text-based documents, update the body without re-uploading the file. (File-based documents still use the existing replace-file flow where applicable.)
SMS conversation metadata: Added SMS support to conversation metadata with SMSConversationInfo, sms as an authorization method and twilio_sms as a conversation initiation source.
Agent configuration updates: Added background music configuration schemas, alerting monitor configuration, 2D layout fields, widget file upload configuration, and new LLM options gpt-5.4-mini, gpt-5.4-nano, gpt-5.4-mini-2026-03-17 and gpt-5.4-nano-2026-03-17.

Workspaces

API request analytics: Added a workspace analytics endpoint for querying API requests with time range, filtering, search, sort and limit controls.
API key IP allowlisting: Added allowed_ips to service account API key create, edit and response schemas. Create requests accept an array of IP addresses or CIDR ranges, or null to allow all IPs. Edit requests also accept clear and no_update.
Workspace permissions: Added conversational_ai_read and voice_design to workspace group permissions.

Voice Design

Voice preview migration: Deprecated POST /v1/text-to-voice/create-previews. Use Design a voice to create previews, then use the returned generated_voice_id when creating a voice.

Voice Changer

WAV output formats: Added wav_8000, wav_16000, wav_22050, wav_24000, wav_32000, wav_44100 and wav_48000 to the output_format query parameter on speech-to-speech conversion.

SDK Releases

Python SDK

v2.47.0 - Regenerated the SDK for the May 12, 2026 API schema. The release adds typed support for RAG chunk listing, file document updates, workspace API request analytics, service account API key IP allowlisting, phone number agent configuration fields, webhook request headers, voice metadata moderation, new LLM options and updated speech-to-speech output formats.

JavaScript SDK

v2.47.0 - Regenerated the SDK for the May 12, 2026 API schema. The release adds typed support for RAG chunk listing, file document updates, workspace API request analytics, service account API key IP allowlisting, phone number agent configuration fields, webhook request headers, voice metadata moderation, new LLM options and updated speech-to-speech output formats.

Packages

@elevenlabs/client@1.7.0, @elevenlabs/react@1.6.0, @elevenlabs/react-native@1.2.0 and @elevenlabs/types@0.13.0 - Added full tool result payload support to onAgentToolResponse. The callback now receives agent_tool_response_full_payload events with the raw full_tool_result string, capped at 64 KB, when enabled in the agent configuration.
@elevenlabs/client@1.6.0, @elevenlabs/react@1.5.0, @elevenlabs/react-native@1.1.6 and @elevenlabs/types@0.12.0 - Added native mute and unmute support to Scribe realtime STT. RealtimeConnection now exposes mute(), unmute() and isMuted, and useScribe exposes matching state and callbacks. The releases also add onAgentResponseCorrection for agent response correction events.
@elevenlabs/client@1.5.0, @elevenlabs/react@1.4.0, @elevenlabs/react-native@1.1.5 and @elevenlabs/types@0.11.0 - Added optional contextId to sendContextualUpdate for deduplicating contextual updates and added llm to the typed agent prompt override for conversation sessions. The React package also allows useScribe microphone deviceId to use full ConstrainDOMString constraints.
@elevenlabs/convai-widget-core@0.12.0 and @elevenlabs/convai-widget-embed@0.12.0 - Added file upload support to the embedded ElevenAgents widget.
@elevenlabs/convai-widget-core@0.12.1 and @elevenlabs/convai-widget-embed@0.12.1 - Fixed text input submission for IME users by ignoring Enter keydowns while composition is active.
@elevenlabs/convai-widget-core@0.12.2 and @elevenlabs/convai-widget-embed@0.12.2 - Updated the widget packages to @elevenlabs/client@1.7.0, including full tool result payload support.
@elevenlabs/convai-widget-core@0.12.3 and @elevenlabs/convai-widget-embed@0.12.3 - Fixed transcript ordering when user and agent messages share the same event_id, so voice and DTMF turns render the user transcript before the agent message.
@elevenlabs/convai-widget-core@0.12.4 and @elevenlabs/convai-widget-embed@0.12.4 - Fixed voice widget transcripts so streamed agent response parts are ignored for voice sessions and late user transcripts are inserted before their matching agent response.

API

View API changes

New Endpoints

ElevenAgents

Get SIP messages for a conversation - GET /v1/convai/conversations/{conversation_id}/sip-messages
- Added required path parameter conversation_id (string)
- Added optional query parameters page_size (integer, default 20) and cursor
- Returns GetSIPLogMessagesResponse with sip_messages, nullable next_cursor and has_more
Get SIP messages for a phone number - GET /v1/convai/phone-numbers/{phone_number_id}/sip-messages
- Added required path parameter phone_number_id (string)
- Added optional query parameters page_size (integer, default 20) and cursor
- Returns GetSIPLogMessagesResponse
Get RAG chunks for a document - GET /v1/convai/knowledge-base/{documentation_id}/chunks
- Added required path parameter documentation_id (string)
- Added required query parameter embedding_model
- Added optional query parameters page_size (integer, default 30) and cursor
- Returns KnowledgeBaseDocumentChunksResponseModel with chunks and nullable next_cursor
Update document file - PATCH /v1/convai/knowledge-base/{documentation_id}/update-file
- Added required path parameter documentation_id (string)
- Added multipart form body with required file (string, binary)
- Returns the updated knowledge base document model

Workspaces

POST /v1/workspace/analytics/requests
- Added request body with optional start_time, end_time, limit (integer, default 100, maximum 1000), sort, filters and search
- Returns WorkspaceAnalyticsQueryResponseModel with columns, column_types, rows and column_units

Updated Endpoints and Schemas

ElevenAgents

Update knowledge base document - PATCH /v1/convai/knowledge-base/{documentation_id}
- Added JSON request body fields name (optional nullable string) and content (optional nullable string)
Create agent - POST /v1/convai/agents/create
- Changed enable_versioning default from false to true
Update agent - PATCH /v1/convai/agents/{agent_id}
- Changed enable_versioning_if_not_enabled default from false to true
Update phone number - PATCH /v1/convai/phone-numbers/{phone_number_id}
- Added environment and branch_id to phone number agent configuration
- store_sip_messages now defaults to true
Get widget - GET /v1/convai/agents/{agent_id}/widget
- Added file_input_config for widget file uploads
LLM enum
- Added gpt-5.4-mini, gpt-5.4-nano, gpt-5.4-mini-2026-03-17 and gpt-5.4-nano-2026-03-17
AuthorizationMethod enum
- Added sms
ConversationInitiationSource enum
- Added twilio_sms
AgentTopicResponseModel
- Added optional nullable parent_topic_id, x_2d and y_2d
BackgroundMusicConfig and BackgroundMusicConfigWorkflowOverride
- Added source_type, source_id, volume and crossfade_loop
- Added BackgroundMusicPresetId enum values city, elevator1, elevator2, elevator3, elevator4, office1, office2, restaurant and typing
AgentPlatformSettingsResponseModel
- Added alerting with Monitor enum values elevated_conversation_failure_rate and elevated_tool_failure_rate
ProcedureCompilerMode enum
- Removed deterministic

Workspaces

Service account API key create and edit schemas
- Added allowed_ips as an optional array of IP addresses or CIDR ranges, with 1 to 100 entries
- Create requests can pass null to allow all IPs
- Edit requests can pass clear or no_update; the default is no_update
WorkspaceApiKeyResponseModel
- Added nullable allowed_ips
WorkspaceGroupPermission enum
- Added conversational_ai_read and voice_design
Auth connection schemas
- Added ApiIntegrationOAuth2CustomAppResponse for user-owned OAuth2 custom app connections

Voice Design

Create voice previews - POST /v1/text-to-voice/create-previews
- Marked as deprecated
- Updated the description to point developers to Design a voice

Voice Changer

Convert speech to speech - POST /v1/speech-to-speech/{voice_id}
- Added wav_8000, wav_16000, wav_22050, wav_24000, wav_32000, wav_44100 and wav_48000 to the output_format enum
- Updated the description to note that PCM and WAV 44.1 kHz formats require Pro tier or higher