Starstruk Logo MarkStarstruk

livekit-agents@1.6.2

snarktank/ralphlivekit-agents@1.6.2Jun 19, 2026by tinalenguyen

AI Summary

Introduces new TTS and STT providers, including Gemini 3.1 flash TTS and Assembly AI universal-3-5-pro, along with various parameter updates for other providers.

Key Highlights

  • Added Gemini 3.1 Flash TTS support with streaming response.
  • Assembly AI universal-3-5-pro (now default) and Voice Focus streaming params.
  • FishAudio speed/volume prosody params added.
  • Soniox support for STT-RT-V5 with endpoint sensitivity option.

New Features

  • Gemini 3.1 Flash TTS support.
  • Assembly AI universal-3-5-pro (default) and Voice Focus streaming params.
  • Assembly AI streaming mode latency/accuracy presets.
  • FishAudio speed/volume prosody params.
  • Soniox STT-RT-V5 support.

Full Release Notes

## What's Changed
* feat(assemblyai): add universal-3-5-pro (now default) and Voice Focus streaming params by @dlange-aai in https://github.com/livekit/agents/pull/6119
* feat: add Gemini 3.1 flash TTS support, implement streaming response … by @thorwebdev in https://github.com/livekit/agents/pull/6134
* (google): fix formatting by @tinalenguyen in https://github.com/livekit/agents/pull/6142
* chore(examples): update livekit-agents version to >=1.6 in requirements.txt by @Bobronium in https://github.com/livekit/agents/pull/6150
* fix(openai): default reasoning_effort to 'none' for mini/nano models by @sarvesh4396 in https://github.com/livekit/agents/pull/6148
* feat(assemblyai): add streaming mode (latency/accuracy preset) param by @dlange-aai in https://github.com/livekit/agents/pull/6156
* feat(fishaudio): add speed/volume prosody params and default to s2.1-pro by @cshape in https://github.com/livekit/agents/pull/6159
* docs: add missing google_gemini_tts.py example to voice agents README by @detail-app[bot] in https://github.com/livekit/agents/pull/6155
* feat(soniox): support stt-rt-v5 with endpoint_sensitivity option by @mihafabcic-soniox in https://github.com/livekit/agents/pull/6126
* fix(xai): expose TTS websocket options by @nightcityblade in https://github.com/livekit/agents/pull/6095
* (phonic) hotfix: add a config that lists tools with forbid-speech-after-tool-call by @arunwpm-work in https://github.com/livekit/agents/pull/6143
* fix(workflows): normalize two-digit years in GetDOBTask by @he-yufeng in https://github.com/livekit/agents/pull/6124
* fix(azure): emit STT recognition usage metrics by @nightcityblade in https://github.com/livekit/agents/pull/6161
* (phonic): reuse ws connection across handoffs by @tinalenguyen in https://github.com/livekit/agents/pull/6163
* (google): surface context exhaustion error by @tinalenguyen in https://github.com/livekit/agents/pull/6144
* (inference): add assembly ai model by @tinalenguyen in https://github.com/livekit/agents/pull/6162
* docs(phonic): add forbid_speech_after_tool_call to README config table by @detail-app[bot] in https://github.com/livekit/agents/pull/6168
* feat(phonic): handle user text input by @tinalenguyen in https://github.com/livekit/agents/pull/6169
* livekit-agents@1.6.2 by @github-actions[bot] in https://github.com/livekit/agents/pull/6170

## New Contributors
* @thorwebdev made their first contribution in https://github.com/livekit/agents/pull/6134
* @sarvesh4396 made their first contribution in https://github.com/livekit/agents/pull/6148

**Full Changelog**: https://github.com/livekit/agents/compare/livekit-agents@1.6.1...livekit-agents@1.6.2