Version Packages

[github-actions]

This PR was opened by the Changesets release GitHub action. When you're ready to do a release, you can merge this and the packages will be published to npm automatically. If you're not ready to do a release yet, that's fine, whenever you add more changesets to main, this PR will be updated.

Releases

livekit-plugins-deepgram@0.7.0

Minor Changes

• use streaming AudioDecoder to handle compressed encoding - #1584 (@davidzhao)

Patch Changes

• added a tts.prewarm method to start the connection pool early. - #1587 (@davidzhao)

• update pool configuration for deepgram and cartesia - #1605 (@jayeshp19)

• set mex session duration to 1 hour in deepgram connection pool - #1582 (@jayeshp19)

• updated livekit-agent reference to <1.0 - #1607 (@davidzhao)

livekit-plugins-elevenlabs@0.8.0

Minor Changes

• use streaming AudioDecoder to handle compressed encoding - #1584 (@davidzhao)

Patch Changes

• added a tts.prewarm method to start the connection pool early. - #1587 (@davidzhao)

• deprecated elevenlabs' optimize_stream_latency option - #1587 (@davidzhao)

• increase elevenlabs websocket connection timeout to default 300 seconds - #1582 (@jayeshp19)

• updated livekit-agent reference to <1.0 - #1607 (@davidzhao)

• Added speed parameter for voices. - #1574 (@MatthiasGruba)

  E.g.:

  voice = Voice(
      id="EXAVITQu4vr4xnSDxMaL",
      name="Bella",
      category="premade",
      settings=VoiceSettings(
          stability=0.71,
          speed=1.2,
          similarity_boost=0.5,
          style=0.0,
          use_speaker_boost=True,
      ),
  )

livekit-plugins-google@0.11.0

Minor Changes

• Add simple video input support for gemini live - #1536 (@bcherry)

Patch Changes

• use streaming AudioDecoder to handle compressed encoding - #1584 (@davidzhao)

• updated livekit-agent reference to <1.0 - #1607 (@davidzhao)

livekit-agents@0.12.17

Patch Changes

• use streaming AudioDecoder to handle compressed encoding - #1584 (@davidzhao)

• added a tts.prewarm method to start the connection pool early. - #1587 (@davidzhao)

• Raise ValueError in FallbackAdapter when streaming is not supported - #1609 (@jayeshp19)

• fixed a bug in AudioStreamDecoder where it could fail on close - #1587 (@davidzhao)

• support for livekit noise cancellation plugin in VoicePipelineAgent and MultimodalAgent - #1551 (@bcherry)

• fix: _play_speech get stuck due to orphan speech handle - #1555 (@SiyuanQi)

livekit-plugins-anthropic@0.2.13

Patch Changes

• updated livekit-agent reference to <1.0 - #1607 (@davidzhao)

livekit-plugins-assemblyai@0.2.3

Patch Changes

• updated livekit-agent reference to <1.0 - #1607 (@davidzhao)

livekit-plugins-aws@0.1.1

Patch Changes

• use streaming AudioDecoder to handle compressed encoding - #1584 (@davidzhao)

• updated livekit-agent reference to <1.0 - #1607 (@davidzhao)

livekit-plugins-azure@0.5.5

Patch Changes

• feat: Azure.STT support profanity_option - #1540 (@shiftu)

• updated livekit-agent reference to <1.0 - #1607 (@davidzhao)

livekit-plugins-browser@0.0.6

Patch Changes

• updated livekit-agent reference to <1.0 - #1607 (@davidzhao)

livekit-plugins-cartesia@0.4.9

Patch Changes

• use streaming AudioDecoder to handle compressed encoding - #1584 (@davidzhao)

• added a tts.prewarm method to start the connection pool early. - #1587 (@davidzhao)

• update pool configuration for deepgram and cartesia - #1605 (@jayeshp19)

• updated livekit-agent reference to <1.0 - #1607 (@davidzhao)

livekit-plugins-fal@0.2.4

Patch Changes

• updated livekit-agent reference to <1.0 - #1607 (@davidzhao)

livekit-plugins-llama-index@0.2.3

Patch Changes

• updated livekit-agent reference to <1.0 - #1607 (@davidzhao)

livekit-plugins-minimal@0.2.2

Patch Changes

• updated livekit-agent reference to <1.0 - #1607 (@davidzhao)

livekit-plugins-nltk@0.7.4

Patch Changes

• updated livekit-agent reference to <1.0 - #1607 (@davidzhao)

livekit-plugins-openai@1.0.1

Patch Changes

• use streaming AudioDecoder to handle compressed encoding - #1584 (@davidzhao)

• fix multimodal agent interrupts itself when creating function call response - #1585 (@longcw)

• feat: add max_tokens option to LLM and LLMStream classes - #1576 (@davidzhao)

• updated livekit-agent reference to <1.0 - #1607 (@davidzhao)

livekit-plugins-playai@1.0.9

Patch Changes

• use streaming AudioDecoder to handle compressed encoding - #1584 (@davidzhao)

• updated livekit-agent reference to <1.0 - #1607 (@davidzhao)

livekit-plugins-rag@0.2.4

Patch Changes

• updated livekit-agent reference to <1.0 - #1607 (@davidzhao)

livekit-plugins-rime@0.2.1

Patch Changes

• use streaming AudioDecoder to handle compressed encoding - #1584 (@davidzhao)

• updated livekit-agent reference to <1.0 - #1607 (@davidzhao)

livekit-plugins-silero@0.7.5

Patch Changes

• updated livekit-agent reference to <1.0 - #1607 (@davidzhao)

livekit-plugins-speechmatics@0.0.2

Patch Changes

• updated livekit-agent reference to <1.0 - #1607 (@davidzhao)

livekit-plugins-turn-detector@0.4.3

Patch Changes

• updated livekit-agent reference to <1.0 - #1607 (@davidzhao)

• retrained to be robust to missing terminal punctuation - #1565 (@jeradf)