November 27, 2025

New LLM support: Extended LLM options with gemini-3-pro-preview model.
Out-of-band DTMF: Added use_out_of_band_dtmf flag to PlayDTMFToolConfig for improved DTMF tone handling in telephony integrations.
Validation improvements: Reduced maximum items for agent test submission from 200 to 100 for both ResubmitTestsRequestModel.test_run_ids and RunAgentTestsRequestModel.tests to improve performance and reliability.
Live analytics: Added new analytics endpoint to retrieve real-time count of active conversations.
Custom LLM API types: Added api_type field to CustomLLM schema with enum CustomLLMAPIType supporting chat_completions and responses options for flexible LLM integration.
Conversation filtering: Enhanced conversation filtering with support for feedback ratings and comments.

Speaker management: Added ability to create new speakers for dubbing resources and migrate segments between speakers.
Speaker updates: Added speaker_name field support when updating dubbing speakers.
Transcript defaults: Relaxed transcript schema requirements with defaults for text, word_type, and speaker_id fields, and removed some required field constraints for easier integration.
Language code support: Clarified that source_lang and target_lang fields expect ISO 639-1/3 codes.

Image asset support: Added ProjectImageResponseModel schema for image assets in projects.
Project assets: ProjectResponseModel.assets now includes ProjectImageResponseModel for better asset management.
Base voices: Added new ProjectResponseModel.base_voices field to project responses.
Chapter voice IDs: Added voice_ids field to chapter response models.

Webhook management: Added comprehensive webhook support with endpoints to create, update, and delete workspace webhooks for better integration capabilities.
Extended billing periods: Expanded billing period options to include 3_month_period and 6_month_period.
Conversation warnings: Added optional warnings array to conversation-related response models.

Enhanced prompts: Refined music prompt descriptions to include “musical directions” for more precise music generation guidance.

v2.25.1 - Fixed PCM binary parsing for Music SDK.
v2.25.0 - Updated SDK to support latest API schema changes including new dubbing endpoints, webhook management, and agent platform improvements.

v2.24.0 - Updated SDK to support latest API schema changes including new dubbing endpoints, webhook management, and agent platform improvements.

@elevenlabs/react@0.12.0 - Fixed participant disconnect handling, added all Scribe event types, and improved iOS device ID handling.
@elevenlabs/react@0.11.3 - Added support for agent tool requests, enabling better integration with Agents Platform tools.
@elevenlabs/react@0.11.2 - Build improvements and version updates.

@elevenlabs/client@0.12.0 - Fixed participant disconnect handling, added all Scribe event types, and improved iOS device ID handling.
@elevenlabs/client@0.11.3 - Added support for agent tool requests, enabling better integration with Agents Platform tools.
@elevenlabs/client@0.11.2 - Build improvements and version updates.
@elevenlabs/client@0.11.1 - Fixed LiveKit URL handling to respect custom LiveKit URLs.

@elevenlabs/react-native@0.5.5 - Fixed participant disconnect handling to properly clean up connections when participants leave.
@elevenlabs/react-native@0.5.4 - Fixed workspace resolution issue.
@elevenlabs/react-native@0.5.3 - Stabilized provider to prevent app reload during calls, added widget markdown renderer, fixed empty stream message handling, and updated Vite dependencies.

@elevenlabs/types@0.4.0 - Added all Scribe event types for comprehensive speech-to-text event handling.
@elevenlabs/types@0.3.1 - Added types provenance for improved package security and integrity.

v3.0.0 - Major release with breaking changes including enhanced disconnect handling with reason parameter, new .thinking agent state, LiveKit 2.10.0+ support, Swift 5.9+ compatibility (down from 6.0 requirement), agent response metadata support, and improved error handling with audio pipeline control.

New Endpoints

Move segments between speakers - Move dubbing segments between different speakers in a dubbing resource.
Create a new speaker - Create a new speaker for a dubbing resource.
Create workspace webhook - Create a new webhook for workspace events.
Update workspace webhook - Update an existing workspace webhook configuration.
Delete workspace webhook - Delete a workspace webhook.
Get live count - Get real-time count of active agent conversations.

Get conversations
- Added rating_max query parameter (integer) for filtering conversations by maximum feedback rating
- Added rating_min query parameter (integer) for filtering conversations by minimum feedback rating
- Added has_feedback_comment query parameter (boolean) for filtering conversations that have feedback comments
Submit batch calling
- Made agent_phone_number_id nullable and optional
- Made phone_number nullable and optional in recipient models
Create agent, Update agent, Get agent
- Added suggested_audio_tags array (up to 20 items) to agent voice configurations
- Added use_out_of_band_dtmf flag to DTMF tool configuration
Agent Testing
- Reduced maxItems from 200 to 100 for test_run_ids in resubmit tests requests
- Reduced maxItems from 200 to 100 for tests array in run agent tests requests

Update dubbing speaker
- Added speaker_name field support for speaker updates
Dubbing transcript endpoints
- Made text, word_type, and speaker_id optional with default values
- Relaxed required field constraints for easier integration

Project endpoints
- Added ProjectImageResponseModel to assets array in project responses
- Added base_voices field to project response models
Chapter endpoints
- Added voice_ids array field to chapter response models

Subscription endpoints
- Extended billing period enums to include 3_month_period and 6_month_period

Custom LLM configuration
- Added api_type field with CustomLLMAPIType enum (chat_completions or responses)
LLM models
- Extended LLM model enum with gemini-3-pro-preview
Music
- Refined prompt descriptions to include “musical directions”
Conversation models
- Added optional warnings array to conversation-related response models