GET STARTED

Changelog

October 27, 2025

Workspaces

  • External voice sharing controls: External voice sharing and Voice Library publishing can now be disabled via workspace groups. Internal (in-organization) voice sharing is not impacted.

Agents Platform

  • Multi-environment agent management: The Agents CLI now supports the --env flag, allowing you to manage agents deployed to multiple accounts simultaneously.
  • Search functionality: Added search parameter to the Get conversations endpoint for filtering conversations.

SDK Releases

JavaScript SDK

  • v2.20.1 - Fixed Music API type definitions and added Realtime Scribe language code support
  • v2.20.0 - Added helper methods for Realtime Scribe with improved ASR capabilities. This is a beta feature and not widely available yet

Python SDK

  • v2.20.1 - Fixed file parameter handling in client methods
  • v2.20.0 - API schema updates and improvements
  • v2.19.0 - Added helper method for Scribe Realtime with improved ASR capabilities. This is a beta feature and not widely available yet

Agents CLI

  • @elevenlabs/agents-cli@0.6.0 - Added support for --env flag to manage agents across multiple accounts, plus bug fixes and reliability improvements

React Native

React

Client

API

Updated Endpoints

Agents Platform

  • Get conversations

    • Added optional search query parameter (string) for full-text or fuzzy search over transcript messages

  • Create agent, Get agent, Update agent

    • Added optional tool_call_sound field to play predefined sounds during tool execution
    • Added optional tool_call_sound_behavior field (default: auto) to control when tool call sounds play

  • Simulate conversation, Simulate conversation stream

    • Added optional tool_call_sound field for tool execution audio feedback
    • Added optional tool_call_sound_behavior field for sound playback control

MCP Servers

  • Update MCP server

    • Added optional execution_mode field to control when and how tools execute (immediate, post_tool_speech, or async)

  • Create MCP server, Get MCP server

    • Added execution_mode field (default: immediate) for tool execution timing control

Server Tools

  • Server tool configuration schemas now support:
    • execution_mode field to control tool execution timing (immediate, post-speech, or async)
    • tool_call_sound and tool_call_sound_behavior fields for audio feedback

Supported LLM Models

  • Added support for new Claude Haiku models:
    • claude-haiku-4-5
    • claude-haiku-4-5@20251001

User Management