Changelog

Eleven v3

v3 is out of alpha - it’s more stable, accurate and has lower latency. Read more about Eleven v3.

Text-to-Dialogue

• WAV output formats: Text-to-Dialogue endpoints now support WAV output formats (wav_8000, wav_16000, wav_22050, wav_24000, wav_32000, wav_44100, wav_48000) in addition to existing MP3, PCM, OPUS, and other formats. WAV formats with 44.1kHz sample rate require a Pro tier subscription or above.

Agents Platform

• Agent branch renaming: You can now rename agent branches using the Update branch endpoint. The new optional name field accepts 1-140 characters.
• Alignment guardrails: Added AlignmentGuardrail type to GuardrailsV1 schema for enhanced conversation safety controls.
• Speculative turn configuration: Added speculative_turn field to turn configuration for fine-tuning agent turn-taking behavior.
• Procedure references: Agent patch requests now support procedure_refs for referencing reusable procedures.
• Webhook response filtering: Added response_filter_mode and response_filters fields to webhook overrides, with new ResponseFilterMode enum for controlling which response data is passed through.
• Error details in tool events: Added raw_error_message field to API integration webhook, system, and workflow tool event models for improved debugging.
• Flexible tool call matching: Testing models now include check_any_tool_matches option to relax tool call matching requirements during agent testing.
• Secrets pagination: Get workspace secrets endpoint now supports pagination with page_size (max 100) and cursor query parameters, returning next_cursor and has_more in responses.

Workspaces

• Permission clarifications: Workspace group and invite endpoints now document specific permission requirements (group_members_manage for group member operations, WORKSPACE_MEMBERS_INVITE for workspace invitations) instead of requiring workspace administrator status.
• New permission types: Added group_members_manage and terms_of_service_accept to the PermissionType enum.

User

• Compliance terms visibility: Added show_compliance_terms field to user response model.

Metrics

• ASR provider tracking: Added convai_asr_provider field to metrics for tracking automatic speech recognition provider usage.

SDK Releases

Python SDK

• v2.34.0 - Added WAV output formats for Text-to-Dialogue, webhook response filtering, agent branch renaming, secrets pagination, and speculative turn configuration
• v2.33.1 - Fixed bug with URL streaming in Scribe
• v2.33.0 - Fixed bug with agent initialization and user_id handling, added audio alignment callback for agent conversations

JavaScript SDK

• v2.34.0 - Added WAV output formats for Text-to-Dialogue, webhook response filtering, agent branch renaming, secrets pagination, and speculative turn configuration

React and Client SDKs

• @elevenlabs/client@0.14.0-beta.0 - Reduced audio chunk length from 250ms to 100ms for lower latency in agent conversations
• @elevenlabs/react@0.14.0-beta.0 - Reduced audio chunk length from 250ms to 100ms for lower latency in agent conversations
• @elevenlabs/client@0.13.1 - Fixed issue where input audio would not re-establish after microphone permission revocation
• @elevenlabs/react@0.13.1 - Fixed issue where input audio would not re-establish after microphone permission revocation

Widget Packages

• @elevenlabs/convai-widget-core@0.8.1 - Fixed microphone mute state reset when call ends to prevent UI/audio desync on subsequent calls
• @elevenlabs/convai-widget-embed@0.8.1 - Fixed microphone mute state reset when call ends
• @elevenlabs/convai-widget-core@0.8.0 - Fixed styling issue in shadow root
• @elevenlabs/convai-widget-embed@0.8.0 - Fixed styling issue in shadow root
• @elevenlabs/convai-widget-core@0.7.0 - Updated Tailwind to v4, added optional dismissable widget parameter, and fixed microphone permission handling
• @elevenlabs/convai-widget-embed@0.7.0 - Updated Tailwind to v4, added optional dismissable widget parameter

API