ElevenLabs Events, Embed Transcripts & SDK Update
- ElevenLabs agent events — underlying ElevenLabs server events are now forwarded via the
elevenlabs_agent_eventevent type, giving you access to raw ElevenLabs Conversational AI events - Transcript on embed — Transcripts are now available directly on embed sessions
- JavaScript SDK updated — Updated the
@heygen/liveavatar-web-sdkpackage with new event types and improvements
Auth Simplification & Session Filtering
- Authentication — Cleaned up documentation for which endpoints require which auth specifications
- New
avatar_idfilter on/v1/sessions— List sessions can now be filtered by an optional avatar_id query parameter
Embeds, Image Avatars & More
- New
/v2/embeddingsendpoint with sandbox support — Embeds can now be created with Sandbox Mode available - Built Image Avatar pipeline — Create a fully animated avatar from just a photo using the new validate and submit endpoints
Improvements
- Update avatar endpoint — You can now change an avatar’s default voice
- Avatar and voice deletion untangled — Deleting a voice no longer affects its associated avatar, and vice versa
- ElevenLabs agent dynamic variables — Configure dynamic variables for ElevenLabs-powered agents that get replaced at session start
- Source events fixed in FULL Mode —
avatar.sayandavatar.repeatevents now correctly returnsource_event_id
ElevenLabs Scribe, Embed Improvements
- Added support for ElevenLabs Scribe, expanding ASR capabilities
- Embed Improvements
- Default language selection, letting users set the language for their embed experience
- Time limits, giving creators control over session duration
Voice Settings & Fish Audio
- Added additional voice settings for more granular control over avatar speech
- Added access to Fish Audio as a TTS provider
- New
[GET] /v1/languagesendpoint to clarify which languages are currently supported
language parameter interacts with FULL Mode systems.ElevenLabs Integration
- The
v1/secretsendpoint now accepts ElevenLabs API keys - FULL Mode sessions can now start with your own ElevenLabs keys and voices
- Added integration with ElevenLabs Agent functionality
LLM Plugin & Session Controls
- Introduced LLM Plugin for custom LLM configurations
- Added customizable session duration controls
- Transcription chunk events are now emitted in real time
- New endpoint to track user credit balances
Session Configuration & LITE Mode
- New session configuration options for video codec selection (H.264 / VP8)
- Added video quality control settings
- Added voice customization options
- CUSTOM Mode has been renamed to LITE Mode (backward-compatible)
- Bug fix: resolved opening line speech issues
Push-to-Talk
- Released Push-to-Talk functionality for avatar sessions
- Added accompanying documentation and integration guides
Sandbox Mode & FULL Mode Improvements
- Introduced Sandbox Mode for testing without credit charges
- Made
contextoptional in FULL Mode configurations, reducing required setup
Custom Mode & Session List Updates
- Custom Mode now exposes LiveKit Agent token for developers to integrate their own agents
- Session List endpoint updated to use query parameters
Transcription Endpoint
- New
[GET] /v1/sessions/{session_id}/transcriptendpoint - Enables developers to retrieve transcriptions between users and avatars in FULL Mode sessions