Skip to content

LiveKit Agents 1.8.10 adds recording controls and voice integrations

Updated LiveKit Agents

Summary

Bitrate settings and new speech plugins arrive with Mistral migration requirements.

Category
Voice agents
Date
Pricing
Not stated in the sources we cited.

LiveKit Agents 1.8.10 lets RecorderIO set recording bitrate and constant-bitrate encoding. Defaults remain unchanged; the option is intended for workflows needing a known encoding mode or more reliable duration interpretation by players.

Speech integrations

The release adds Reson8 batch and realtime transcription, including server-side turn detection. It also adds Voxtral 3 speech models and voice presets, Inworld's TTS flash model, and typed AssemblyAI TTS support through LiveKit Inference. Availability and provider billing remain separate from installing the framework.

Mistral users need a migration check

api_mode is ignored, and Chat Completions integrations should move to Conversations. Batch recognition needs an explicit batch model; removed older model IDs must be replaced. Standalone realtime streams without VAD or server-side turn detection need an explicit flush.

The Mistral dependency range and default models change, and Silero is no longer loaded automatically. Worker health returns 503 before registration and after disconnection exceeds the grace period. Test readiness probes and turn-detection settings rather than assuming an existing voice deployment behaves identically.

See the livekit-agents hub.

More from LiveKit Agents

View all

Questions

What is LiveKit Agents?

The documentation says the framework lets you add Python or Node.js programs to LiveKit rooms as realtime participants. The repository describes it as a framework for building realtime voice AI agents.

Is LiveKit Agents open source?

Yes. The GitHub API reports Apache-2.0 for livekit/agents.

What is the latest release covered here?

livekit-agents@1.8.11, published November 5, 2026. It adds inference.responses.LLM (REST by default, optional WebSocket), Zoom AI STT, Kalpa TTS, Rime STT and Prism, Fish Audio realtime STT, OpenAI and Gemini live translate models, and moves Respeecher WebSocket API keys into handshake headers.

Where can agents be deployed?

The documentation says agents can be deployed to LiveKit Cloud or any custom environment.

Filed on Agent Radar. Claims in this note are limited to the sources above.