Data and AI releases

2,224 this month · 171 companies

All changes: Python SDK

UpdateNot yet verified

- v2.75.0 - Added the callback_disconnect option to Conversation and AsyncConversation. It receives a DisconnectionDetails with a reason of "user", "agent" or "error", plus the WebSocket close code and reason when available, and replaces the deprecated callback_end_session.

AI agentsDeveloper tools

Read on elevenlabs.io

Also shipped Oct 26, 2026ElevenLabs in October 2026 →

More from ElevenLabsEvery ElevenLabs release →

Fast LLM service tier

ElevenAgents now offers a fast service tier for supported LLMs, providing higher token throughput and lower latency at a price premium. This can be configured per agent via the prompt configuration.

Update
Source ↗

Clone strength for v4 voices

Text to Speech and Text to Dialogue requests now support a clone_strength parameter for v4 voices. This allows users to control how closely the generated audio follows the training samples of a Professional Voice Clone.

Update
Source ↗

Expiring service account API keys

Service account API keys can now be configured with expiration dates. Keys can be set to expire between 15 minutes and 90 days, improving security for workspace integrations.

Update
Source ↗

All changes: JavaScript SDK

- v2.75.0 - client.speechToSpeech.convert and client.speechToSpeech.stream now call POST /v1/voice-changer/{voice_id} and its /stream path. Added client.environmentVariables.delete, client.conversationalAi.tests.invocations.update for renaming a test invocation, and an optional name on client.conversationalAi.agents.runTests.

Update
Source ↗

All changes: Android SDK

- v0.13.0 - agent_tool_request is now handled as a notification event instead of a client tool call, so client tools no longer run twice, the first time without parameters. The SDK also no longer crashes when a client tool answers after the connection has closed.

Update
Source ↗

All changes: ElevenLabs CLI

- v1.7.1 - say uses eleven_v4 and new agent templates use eleven_v4_turbo by default. Fixes onboard sign-in on Windows and when the token cannot be saved to the keychain.

Update
Source ↗

All changes: Packages

- @elevenlabs/client@1.29.0 and @elevenlabs/react@1.19.0 - Added the onAudioAlignmentPlayback callback, called with { event_id, alignment } when an aligned audio chunk starts playing, for syncing text with speech. It is not called on WebRTC connections.

Update
Source ↗