livekit-agents@1.5.7

livekit/agentslivekit-agents@1.5.7Apr 30, 2026by tinalenguyen

AI Summary

A maintenance release focusing on bug fixes for STT and TTS plugins, addition of new AI model support (GPT-5.4-mini, XAI), and improvements to metrics and session handling.

Key Highlights

  • Added support for GPT-5.4-mini model
  • Added Grok voice model support via XAI plugin
  • Fixed various bugs in ElevenLabs, Soniox, and Cartesia plugins
  • Added playback_latency metric for monitoring
  • Added inference_class option for priority routing

New Features

  • New model registries (GPT-5.4-mini, XAI grok-voice-think-fast)
  • Exposure of provider request IDs for debugging
  • Support for timestamps in Inference
  • Dynamic endpointing alpha parameter support

Full Release Notes

## What's Changed
* fix(openai): forward session.update on RealtimeModel.update_options by @longcw in https://github.com/livekit/agents/pull/5531
* fix(transcription): seed _start_wall_time fallback in aclose by @longcw in https://github.com/livekit/agents/pull/5532
* Fix realtime reply generation after interruption by @jayeshp19 in https://github.com/livekit/agents/pull/5526
* fix(cartesia): Move API key from Query Params to Headers by @charlotte-zhuang in https://github.com/livekit/agents/pull/5516
* deepgram-stt: report connection-lifetime remainder so usage matches billing by @joaquinhuigomez in https://github.com/livekit/agents/pull/5506
* feat(room-io): add json_format option for timed transcription output by @longcw in https://github.com/livekit/agents/pull/5472
* feat(inference): add inference_class option to LLM for priority routing by @adrian-cowham in https://github.com/livekit/agents/pull/5517
* chore: update default model for Anthropic LLM by @royalfig in https://github.com/livekit/agents/pull/5539
* fix(voice): pause output when user starts speaking during thinking by @longcw in https://github.com/livekit/agents/pull/5535
* feat(openai): add gpt-5.4-mini to model registry by @xtreme-sameer-vohra in https://github.com/livekit/agents/pull/5540
* feat(assemblyai): warn when audio stops flowing to the WebSocket by @gsharp-aai in https://github.com/livekit/agents/pull/5504
* feat(tts): add support for timestamps in Inference by @chenghao-mou in https://github.com/livekit/agents/pull/5534
* docs: clarify RunResult.events testing surface by @Rul1an in https://github.com/livekit/agents/pull/5525
* feat(stt): back-date START_OF_SPEECH onset via server-provided timestamp by @gsharp-aai in https://github.com/livekit/agents/pull/5479
* feat(aws): add auto language detection and mid-stream language switch… by @cldsime in https://github.com/livekit/agents/pull/5435
* (release workflow): add docs job by @tinalenguyen in https://github.com/livekit/agents/pull/5551
* (liveavatar): add video_quality param by @tinalenguyen in https://github.com/livekit/agents/pull/5552
* Add avatartalk plugin to optional dependencies by @bcherry in https://github.com/livekit/agents/pull/5550
* fix(soniox): emit PREFLIGHT_TRANSCRIPT for preemptive LLM generation by @octo-patch in https://github.com/livekit/agents/pull/5553
* feat(xai): support model selection in realtime, default to grok-voice-think-fast-1.0 by @Hormold in https://github.com/livekit/agents/pull/5548
* Remove 'distil-whisper-large-v3-en' from STTModels by @vedevpatel in https://github.com/livekit/agents/pull/5537
* fix: don't swallow _ExitCli during shutdown by @lawrence3699 in https://github.com/livekit/agents/pull/5519
* feat: expose provider request ids on STT/TTS/LLM spans for debugging by @longcw in https://github.com/livekit/agents/pull/5546
* chore(openai): remove STT.with_groq constructor by @davidzhao in https://github.com/livekit/agents/pull/5555
* chore(deps): update github actions (major) by @renovate[bot] in https://github.com/livekit/agents/pull/5558
* feat(mcp): allow updating headers on MCPServerHTTP by @longcw in https://github.com/livekit/agents/pull/5559
* feat(metrics): add playback_latency metric by @longcw in https://github.com/livekit/agents/pull/5524
* feat(endpointing): expose dynamic endpointing alpha parameter (AGT-2764) by @chenghao-mou in https://github.com/livekit/agents/pull/5491
* fix(smallestai): use close_stream signal to properly terminate STT session by @harshitajain165 in https://github.com/livekit/agents/pull/5562
* Hotfix; Updated default Avatar ID by @hari-truviz in https://github.com/livekit/agents/pull/5568
* fix(gemini live): use parameters instead of parameters_json_schema for raw schema function tools by @longcw in https://github.com/livekit/agents/pull/5560
* Stuck aclose() activity leading to stuck handoff by @svacatalisan in https://github.com/livekit/agents/pull/4649
* fix(async_toolset): respect allow_interruptions when cancelling tool calls by @longcw in https://github.com/livekit/agents/pull/5570
* update livekit rtc to 1.1.7 by @davidzhao in https://github.com/livekit/agents/pull/5572
* feat(mistral): add connectors provider tool & fix realtime STT custom headers by @jeanprbt in https://github.com/livekit/agents/pull/5575
* feat(openai): expose verbosity in Responses LLM by @AlessandroElyos in https://github.com/livekit/agents/pull/5583
* fix(mistral): use conversations API statelessly by @TheCodingCvrlo in https://github.com/livekit/agents/pull/5586
* support LIVEKIT_AGENT_NAME env var by @theomonnom in https://github.com/livekit/agents/pull/5571
* fix(recorder): use libopus when possible by @chenghao-mou in https://github.com/livekit/agents/pull/5579
* docs: add LIVEKIT_AGENT_NAME to environment variables by @detail-app[bot] in https://github.com/livekit/agents/pull/5599
* fix(elevenlabs): use audio_format query param for STT realtime by @longcw in https://github.com/livekit/agents/pull/5574
* fix: clear stale paused speech state across generation steps by @longcw in https://github.com/livekit/agents/pull/5594
* fix: cancel Runway realtime sessions on shutdown by @robinandeer in https://github.com/livekit/agents/pull/5612
* fix(inference): skip unknown message warning and rename event name by @chenghao-mou in https://github.com/livekit/agents/pull/5614
* feat: add SLNG plugin for STT and TTS by @metehan-slng in https://github.com/livekit/agents/pull/5249
* livekit-agents@1.5.7 by @github-actions[bot] in https://github.com/livekit/agents/pull/5615

## New Contributors
* @charlotte-zhuang made their first contribution in https://github.com/livekit/agents/pull/5516
* @xtreme-sameer-vohra made their first contribution in https://github.com/livekit/agents/pull/5540
* @Rul1an made their first contribution in https://github.com/livekit/agents/pull/5525
* @cldsime made their first contribution in https://github.com/livekit/agents/pull/5435
* @octo-patch made their first contribution in https://github.com/livekit/agents/pull/5553
* @vedevpatel made their first contribution in https://github.com/livekit/agents/pull/5537
* @lawrence3699 made their first contribution in https://github.com/livekit/agents/pull/5519
* @svacatalisan made their first contribution in https://github.com/livekit/agents/pull/4649
* @AlessandroElyos made their first contribution in https://github.com/livekit/agents/pull/5583
* @TheCodingCvrlo made their first contribution in https://github.com/livekit/agents/pull/5586
* @detail-app[bot] made their first contribution in https://github.com/livekit/agents/pull/5599
* @metehan-slng made their first contribution in https://github.com/livekit/agents/pull/5249

**Full Changelog**: https://github.com/livekit/agents/compare/livekit-agents@1.5.6...livekit-agents@1.5.7