Skip to content

@livekit/agents@1.6.5

Latest
Latest

Choose a tag to compare

View all tags
@tinalenguyen tinalenguyen released this 09 Jul 19:12
livekit-agents@1.6.5
dbc38df
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

What's Changed

  • fix(google): broaden _is_gemini_3_flash_model to cover all Gemini 3 Flash variants by @balazssandor in #6210
  • fix(assemblyai): respect mode preset for turn-silence; remap deprecated u3-pro by @dlange-aai in #6220
  • Move frame processor url/token/stream info to client sdk by @1egoman in #5867
  • fix(worker): exit when connection fails after max retries by @longcw in #6103
  • fix(voice): don't re-issue in-flight tool calls on a new turn by @longcw in #6227
  • (phonic): Use stream_ahead_of_real_time mode for Phonic WebSocket and sample rate 24000 by @qionghuang6 in #6236
  • fix(anthropic): use non-whitespace trailing dummy to satisfy provider validation by @JasonGordonD in #6216
  • fix(deepgram): sync missing STT/TTS API params, fix duplicate languages, add TTS model list by @Namit1867 in #5362
  • chore(deps): update dependency msgpack to v1.2.1 [security] by @renovate[bot] in #6243
  • docs: fix hotel_receptionist architecture section after refactor by @detail-app[bot] in #6230
  • fix(deepgram): remove duplicate redact param by @longcw in #6245
  • fix(openai): delete trimmed empty audio items by @he-yufeng in #5887
  • fix(openai realtime): discard orphaned response after interrupt or timeout by @longcw in #6244
  • fix CI due to realtime_model test by @davidzhao in #6261
  • fix: preserve transcription item id by @nightcityblade in #6120
  • fix(openai): skip realtime truncate when no audio was played fixes : #6157 by @ByteMaster-1 in #6158
  • feat(assemblyai): add language_code streaming param for language steering by @gsharp-aai in #6219
  • fix(xai): emit interim transcripts for in-progress status in realtime by @ByteMaster-1 in #6272
  • conversation-aware STT recognition (keyterms + chat context) by @longcw in #6039
  • Allow LemonSlice avatars to join third party meeting platforms by @aweitz in #6233
  • (xai realtime): pass voice parameter by @tinalenguyen in #6276
  • feat(certifi): user certifi as a fallback when system store is not present by @chenghao-mou in #6231
  • chore(eot): update log message about slow stt transcript by @chenghao-mou in #6179
  • fix(fallback_adapter): update stream start time offset in stt fallbackadapter by @chenghao-mou in #6246
  • feat(voice): stream tool call status events by @longcw in #6100
  • set default shutdown reason by @davidzhao in #6284
  • bump worker drain timeout to 1hr by @chenghao-mou in #6286
  • feat(rime): support speed_alpha for arcana and coda models by @balazssandor in #6287
  • feat(deepgram): apply Flux option updates in-band by @longcw in #6277
  • feat: realtime model fallback adapter by @longcw in #6282
  • update keyterm detection default model by @longcw in #6289
  • fix(eot): tighten eot cancellation by speech acitivity by @chenghao-mou in #6274
  • silero: use onnx when explicitely using silero.VAD.load() by @theomonnom in #6290
  • fix(openai): emit start/end of speech events for realtime STT AGT-3051 by @chenghao-mou in #6297
  • feat(smallestai): word_timestamps for TTS, v4 STT endpoints, eou_timeout fix by @harshitajain165 in #5953
  • fix(aws): nest endpointingSensitivity under turnDetectionConfiguration for Nova Sonic 2 by @St-Luciferr in #6201
  • switch to blingfire tokenizer by default by @davidzhao in #6301
  • feat(plugins-tavus): rename replica/persona to face/pal by @carolin-tavus in #6239
  • fix(openai): avoid mutating raw tool schemas for Responses by @VectorPeak in #6305
  • feat(openai): add temperature parameter to STT by @longcw in #6307
  • fix(liveavatar): preserve provider status errors by @VectorPeak in #6306
  • fix incorrect attribution of latency in tts.ttfb by @davidzhao in #6300
  • update livekit to 1.1.13 by @davidzhao in #6311
  • fix(voice): race between session.run and an in-flight AgentTask handoff by @longcw in #6315
  • fix(voice): resolve video task leak in AgentSession by @Mayank-MSJ-Singh in #6318
  • Add remove() method to ChatContext for flexible item removal by @3eid in #5131
  • fix: expose speech generation errors via SpeechHandle.exception() by @longcw in #6304
  • chore(deps): update actions/checkout action to v7 by @renovate[bot] in #6325
  • fix(test): stop false-positive "Audio data isn't PCM" failures in TTS tests by @u9g in #6331
  • feat(anam) add director notes config by @sr-anam in #6267
  • fix(aws): preserve image format for Bedrock images by @VectorPeak in #6328
  • (feat) 11Labs STT : Add enable_logging by @Ludobaka in #6273
  • feat: expressive mode by @tinalenguyen in #6116
  • Add connection pooling for xAI TTS by @godququ5-code in #6317
  • voice: output retries for run(output_type=...) by @theomonnom in #6080
  • disable openai sdk max_retries by @chenghao-mou in #6341
  • Allow direct image uploads for LemonSlice avatars by @jp-lemon in #6343
  • remove structured LLM output from voice pipeline by @tinalenguyen in #6345
  • remove livekit-blingfire (moved) by @theomonnom in #6320
  • (expressive mode): expression marker dialect by @tinalenguyen in #6347
  • (expressive mode): fix markup tags impacting pacing by @tinalenguyen in #6350
  • feat(core): add plain_text_content property for ChatMessage by @chenghao-mou in #6348
  • fix(tts): restart ChunkedStream retries under a fresh request_id by @u9g in #6346
  • send ServerInfo to CLI host on start by @davidzhao in #6260
  • docs: fix livekit-durable README title copied from removed blingfire plugin by @detail-app[bot] in #6355
  • Feat/updating documentation for Gnani by @Gnani-AI-Mintlify in #6004
  • feat(soniox): support speed parameter in TTS by @yui0303 in #6339
  • fix(azure): recover from STT error cancellations instead of hanging by @apoorva-01 in #6362
  • fix: honor IGNORE_ON_ENTER for tools inside a Toolset by @longcw in #6361
  • fix: send DTMF to the active session room by @longcw in #6360
  • docs(soniox): add speed parameter to TTS example in README by @detail-app[bot] in #6366
  • (expressive mode): hide and remove from examples by @tinalenguyen in #6370
  • fix(core): flip text content fields AGT-3103 by @chenghao-mou in #6353
  • livekit-agents@1.6.5 by @github-actions[bot] in #6371

New Contributors

Full Changelog: https://github.com/livekit/agents/compare/livekit-agents@1.6.4...livekit-agents@1.6.5

Contributors

davidzhao, 1egoman, and 29 other contributors
Assets 2
Loading