Update LiveKit dependencies (non-major) to v1.2.18 #6

renovate · 2025-09-02T23:02:18Z

This PR contains the following updates:

Package	Change	Age	Confidence
livekit-agents	`==1.2.7` -> `==1.2.18`
livekit-plugins-deepgram	`==1.2.7` -> `==1.2.18`
livekit-plugins-openai	`==1.2.7` -> `==1.2.18`
livekit-plugins-silero	`==1.2.7` -> `==1.2.18`

Release Notes

livekit/agents (livekit-agents)

`v1.2.18`

Compare Source

What's Changed

chore: update to correct livekit-plugins-minimax-ai package by @davidzhao in #3753
New Spitch STT model: Mansa v1 by @temibabs in #3748
add missing file error for turn detection model by @tinalenguyen in #3755
Add Language Parameter Support for Rime Arcana TTS Model by @gokuljs in #3757
Update Letta voice API integration to use new endpoint by @cpfiffer in #3736
livekit-blingfire v1.0.1 by @theomonnom in #3763
fix blingfire windows compilation for python 3.14-freethreaded by @theomonnom in #3766
allow elevenlabs language code parameter to be null by @tinalenguyen in #3761
changes default base url for spelling by @aryeila in #3768
Improve streaming handling for Neuphonic by @alexshelkov in #3703
turn-detector: add turn detector v0.4.0-intl by @lwestn in #3764
fix(google): improved handling of tool_response_scheduling by @davidzhao in #3781
Update stt.py - Deepgram plugin allows PT for Keyterms by @cateet in #3786
skip exception log for StopResponse from a tool call by @longcw in #3790
restore root otel context for AgentTask and generate_reply in entrypoint by @longcw in #3772
feat: add preflight transcript via utterance by @dan-ince-aai in #3654
fix(google): do not pass in scheduling parameter by default by @davidzhao in #3793
Add Fish Audio TTS Plugin for LiveKit Agents by @ywkim in #3720
Shubhra/nvidia plugins by @Shubhrakanti in #3392
Undo basic_agent accidental commit in #3392 by @Shubhrakanti in #3797
fix: bithuman prewarm credential issue by @CathyL0 in #3794
Added missing parameters to Gladia by @Karamouche in #3796
livekit-agents 1.2.18 by @theomonnom in #3806

New Contributors

@cpfiffer made their first contribution in #3736
@aryeila made their first contribution in #3768
@cateet made their first contribution in #3786
@ywkim made their first contribution in #3720
@Karamouche made their first contribution in #3796

Full Changelog: https://github.com/livekit/agents/compare/[email protected]@1.2.18

`v1.2.17`

Compare Source

What's Changed

Fix/aws realtime tooluse barge in by @kachenjr in #3704
reset user state from away when user input transcribed by @longcw in #3716
set _read_audio_atask to None in init by @tinalenguyen in #3727
add issue templates by @tinalenguyen in #3689
feat: gemini session resumption handle by @aryanvdesh in #3735
turn detection: model v0.3.1-intl by @lwestn in #3724
fix room io audio output deadlock by @longcw in #3746
added gemini live model by @tinalenguyen in #3750
add openai gpt-5-chat-latest model by @tinalenguyen in #3741

New Contributors

@kachenjr made their first contribution in #3704
@aryanvdesh made their first contribution in #3735

Full Changelog: https://github.com/livekit/agents/compare/[email protected]@1.2.17

`v1.2.16`

Compare Source

What's Changed

Conditional message truncation based on LLM capabilitities by @hadamove-rapidsos in #3655
AWS realtime: make ModelStreamErrorException recoverable by @longcw in #3662
use inference gateway in basic_agent by @longcw in #3611
chore: use self.chat_ctx in multi_agent example by @longcw in #3663
fix(speechmatics): AdditionalVocab configuration update by @sam-s10s in #3676
chore(cartesia): default to the latest API version by @davidzhao in #3652
Update Soniox STT parameters by @matejmarinko-soniox in #3670
Improve gcp vertex credential check by @ChenghaoMou in #2798
Add streaming support for Neuphonic by @alexshelkov in #3182
Unify generate_reply and say code pattern by @ChenghaoMou in #3683
chore: correct minimax-ai package name by @davidzhao in #3682
fix(cartesia,deepgram): correctly timeout while in middle of TTS synthesis by @davidzhao in #3686
feat(voice/run_result): OTEL tracing of judge by @bml1g12 in #3639
feat: add CometAPI integration to OpenAI plugin by @TensorNull in #3641
Configure Prometheus in multi process mode by @efontan-dialpad in #3565
Fix: Connection Pool race condition by @adrian-cowham in #3705
chore: lock onnxruntime to <=1.23.1 by @davidzhao in #3712
fix(worker): ensure safe iteration over process pool during job joining by @Panmax in #3710
feat(cartesia): sonic-3 by @davidzhao in #3715

New Contributors

@hadamove-rapidsos made their first contribution in #3655
@matejmarinko-soniox made their first contribution in #3670
@TensorNull made their first contribution in #3641
@efontan-dialpad made their first contribution in #3565

Full Changelog: https://github.com/livekit/agents/compare/[email protected]@1.2.16

`v1.2.15`

Compare Source

What's Changed

reduce CI noise by @theomonnom in #3552
automatically update livekit-agents pyproject.toml optional dependencies on version bump by @theomonnom in #3553
added drain param to session.shutdown() by @tinalenguyen in #3562
fix stt final transcript triggers user turn in manual turn detection by @longcw in #3559
feat(livekit-plugins-hume): add model_version parameter by @zgreathouse in #3563
fix model provider and metrics for FallbackAdapter and StreamAdapter by @longcw in #3526
handle aiohttp client error when connecting to openai realtime api by @longcw in #3574
Add timeout param to with_openrouter() function by @msaelices in #3538
Add a dev folder for examples to keep the git graph clean by @Shubhrakanti in #3582
Ensure ctx.api uses WorkerOptions credentials by exporting LIVEKIT_* in worker by @hwuiwon in #3581
feat(google): Add thinking_config support, new model, and expanded voice profiles for google gemini TTS by @hwuiwon in #3583
chore: ensure a recent version of certifi is installed by @davidzhao in #3580
fix(deepgram): correctly handle timeout related errors by @davidzhao in #3579
realtime model: wait for generate_reply before update tool results by @longcw in #3511
fix aws realtime deps version by @longcw in #3592
Updating Cartesia Version by @namantalreja in #3570
fix: lock pyav to <16 due to build issue by @davidzhao in #3593
lift google realtime api out of beta by @tinalenguyen in #3614
catch delete_room errors and disable delete_room_on_close by default by @longcw in #3600
feat(telemetry/utils): add ttft reporting to LangFuse by @bml1g12 in #3594
Add RTZR(ReturnZero) STT Plugin for LiveKit Agents by @kimdwkimdw in #3376
chore: Remove duplicate docstring for preemptive_generation parameter in AgentSession by @m-hamashita in #3624
fix(deepgram): send CloseStream message before closing TTS WebSocket by @Nisarg38 in #3608
feat(speechmatics): add max_speakers parameter for speaker diarization by @nsepehr in #3524
Align Google STT plugin with official documentation by @mrkowalski in #3628
add backwards compatibility for google's realtime model by @tinalenguyen in #3630
fix: exclude temperature parameter for gpt-5 and similar models by @TheAli711 in #3573
turn_detection: reduce max_endpointing_delay to 3s by @lwestn in #3640
feat: Integrate streaming endpoints for Sarvam APIs by @shreyas-sarvam in #3498
fix: heartbeat by @zachkamran in #3648
enable zero retention mode in elevenlabs by @tinalenguyen in #3647
Unprompted STT Reconnection at startup by @adrian-cowham in #3649
fix #3650 cartesia version backward compatibility by @wlbksy in #3651
livekit-agents 1.2.15 by @theomonnom in #3658

New Contributors

@hwuiwon made their first contribution in #3581
@namantalreja made their first contribution in #3570
@kimdwkimdw made their first contribution in #3376
@m-hamashita made their first contribution in #3624
@Nisarg38 made their first contribution in #3608
@nsepehr made their first contribution in #3524
@TheAli711 made their first contribution in #3573
@lwestn made their first contribution in #3640
@shreyas-sarvam made their first contribution in #3498
@adrian-cowham made their first contribution in #3649

Full Changelog: https://github.com/livekit/agents/compare/[email protected]@1.2.15

`v1.2.14`

Compare Source

New feature

Introduce LiveKit Inference: a unified model interface enabling STT, LLM, and TTS via one API key, with optimized latency, billing, and concurrency management 🚀
https://blog.livekit.io/introducing-livekit-inference/

What's Changed

inference: fix extra_headers provider by @theomonnom in #3549

Full Changelog: https://github.com/livekit/agents/compare/[email protected]@1.2.14

`v1.2.13`

Compare Source

What's Changed

Gladia STT: support partial transcriptions by @fabrice404 in #3530
support STT with model:lang and parse model specs outside ctor by @longcw in #3536
update inference API & update model names by @theomonnom in #3545
deepgram: support for Flux by @davidzhao in #3245

New Contributors

@fabrice404 made their first contribution in #3530

Full Changelog: https://github.com/livekit/agents/compare/[email protected]@1.2.13

`v1.2.12`

Compare Source

What's Changed

fix: add transaction id for bithuman agent by @CathyL0 in #3313
flush audio emitter if audio generation is slower than realtime by @longcw in #3438
docs(CONTRIBUTING.md): add linting/formatting command guideline by @bml1g12 in #3436
feat: add model attribute to metrics tracking in LLM by @Panmax in #3456
Add Fireworks AI STT plugin by @yunyichi in #2687
fix(agent_activity): correctly nest OpenTelemetry spans within existing spans by @bml1g12 in #3454
fixed noise reduction type by @tinalenguyen in #3469
allow VoiceActivityVideoSampler to be disabled with 0fps by @davidzhao in #3474
fix playback_finished rpc for datastream audio output when using thread by @longcw in #3473
add minimax tts plugin by @longcw in #3475
expose background audio track publication for retrieving track details by @s-hamdananwar in #3480
refactor: simplify say() method logic in AgentSession by @Panmax in #3488
refactor: remove redundant if conditions by @Panmax in #3486
gemini realtime: support NON_BLOCKING tool behavior by @longcw in #3482
add docstring for minimax options by @longcw in #3487
inference: support lang/ for stt and update models by @longcw in #3481
add delete_room_on_close to RoomInputOptions by @tinalenguyen in #3467
return RealtimeModelBeta for Azure OpenAI Realtime by @tinalenguyen in #3497
feat: Add OpenRouter plugin for LiveKit Agents by @Hormold in #3167
Add model and provider in metrics for all services by @ChenghaoMou in #3165
add tts_text_transforms as an option to AgentSession by @longcw in #3424
fix: prevent deadlock in speech scheduling after consecutive delay by @Panmax in #3502
Add soniox and fireworks extras by @bcherry in #3491
fix conflicts of metrics.metadata by @longcw in #3501
fix ttft for OpenAI realtime model by @longcw in #3507
fix OAI realtime: remove deepcopy when reconnection by @longcw in #3505
gateway: update inference models by @longcw in #3508
fix datastream io clear buffer rpc for thread executor by @longcw in #3514
fix gemini llm: avoid mixing tool output and user message in a single turn by @longcw in #3509
fix missing simultaneous message & tool call by @furious-luke in #3517
livekit-agents 1.2.12 by @theomonnom in #3523

New Contributors

@yunyichi made their first contribution in #2687
@Hormold made their first contribution in #3167
@furious-luke made their first contribution in #3517

Full Changelog: https://github.com/livekit/agents/compare/[email protected]@1.2.12

`v1.2.11`

What's Changed

add shutdown method for AgentSession by @tinalenguyen in #3429
fixes #3435 by @mrkowalski in #3437
fix(openai): correctly handle update_options for active sessions by @davidzhao in #3448
fix openai realtime with azure when input_audio_noise_reduction is not given by @longcw in #3451
feat: trace Realtime Model Token/Cost via OpenTelemetry by @longcw in #3439
fix oai realtime options with default null by @longcw in #3458
Bug fix: Safe handling in ChatContext.truncate() when fewer items than max_items by @adianliusie in #3457
fix silero vad speech_buffer_max_reached by @longcw in #3452
[Cartesia] Upgrade Default Voice by @chongzluong in #3446

New Contributors

@adianliusie made their first contribution in #3457

Full Changelog: https://github.com/livekit/agents/compare/[email protected]@1.2.11

`v1.2.9`

Compare Source

Features:

OpenAI Realtime API now supports video input

What's Changed

Add Ultravox Realtime API Plugin by @moadel321 in #2992
fix and clean ultravox realtime API plugin by @longcw in #3339
remove sentence tokenizer from transcription sync by @longcw in #3334
non-stream tts: raise no audio pushed error only if text is not empty by @longcw in #3310
fix speech resume when interrupted by interim transcript by @longcw in #3299
add preferred_alignment and fix alignment chars by @longcw in #3341
feat: Add support for Nebius AI Studio Models by @Arindam200 in #3332
feat(AWS): Enable prompt caching by @itskyf in #3338
plugins: groq: llm: add support for timeout and max_retries by @ssettle-groq in #3350
plugins: groq: llm: add support for service_tier by @ssettle-groq in #3348
Fix warning in model field access by @marctorsoc in #3340
chore(groq): accept additional options by @davidzhao in #3370
add ELEVEN_API_KEY to README for configuration by @Panmax in #3371
feat(azure-stt): add configurable punctuation option to Azure STT by @sarthakgoyal23 in #3326
fix transcription synchronizer cannot be closed if paused by @longcw in #3378
chore: add update_options for aws tts by @longcw in #3384
add text normalization param by @tinalenguyen in #3390
fix: improve FallbackAdapter streaming capability detection by @bnovik0v in #3294
fix user speaking span duration by @tinalenguyen in #3404
add realtime model tool calls to chat ctx by @longcw in #3345
make flush duration configurable in commit_user_turn by @longcw in #3358
use markdown and emoji filters for tts_node by default by @longcw in #3305
commit user turn before closing the AgentSession by @longcw in #3377
fix OAI realtime response created after generate_reply timeout by @longcw in #3405
add warning if use_tts_aligned_transcript is enabled but no transcript received from tts by @longcw in #3409
fix: Agent status was not updated when audio was paused. by @Panmax in #3406
don't ever send meta to openai by @guidodecaso in #3402
Revert "tune vad min_silence_duration and min_endpointing_delay (#2953)" by @longcw in #3416
Removed OpenAI-Beta header as per the docs by @MajorTal in #3412
add tool call and output to session.history by @longcw in #3316
fix(sarvam-tts): add bulbul:v3-beta support and make pitch/loudness optional by @21lakshh in #3413
chore: add keyterms support for AssemblyAI plugin by @dan-ince-aai in #3387
Revert "Removed OpenAI-Beta header as per the docs" by @longcw in #3419
feat(Google): Add markup for TTS HD voices by @itskyf in #3281
feat: update openai realtime API version to GA by @davidzhao in #3420
revert #3206, do not auto enable use_tts_aligned_transcript by @longcw in #3423
livekit-agents 1.2.9 by @theomonnom in #3428

New Contributors

@moadel321 made their first contribution in #2992
@Arindam200 made their first contribution in #3332
@ssettle-groq made their first contribution in #3350
@marctorsoc made their first contribution in #3340
@sarthakgoyal23 made their first contribution in #3326
@21lakshh made their first contribution in #3413

Full Changelog: https://github.com/livekit/agents/compare/[email protected]@1.2.9

`v1.2.8`

Compare Source

Features:

AgentSession.start() now returns a RunResult when called with capture_run=True.
This makes it possible to assert the first message when the agent initiates the conversation:

result = await sess.start(EchoAgent(), capture_run=True)
result.expect.next_event().is_agent_handoff(new_agent_type=EchoAgent)
result.expect.next_event().is_message(role="assistant")

Agent false interruptions are now automatically resumed after the false_interruption_timeout. Audio output is paused and then resumed on the same SpeechHandle, eliminating the need to manually call generate_reply() in the agent_false_interruption event handler—please remove this call if present from earlier versions. This behavior is enabled by default; to disable automatic resume, set resume_false_interruption=False.

What's Changed

fix: start datastream audio output right after room connected by @longcw in #3270
add AudioOutput capabilities and disable pause/resume for if output not supported by @longcw in #3269
fix (11labs): fix empty text input and timeout for the first audio chunk by @longcw in #3284
chore: switch to gpt-realtime as default OAI realtime model by @davidzhao in #3287
fix(plugins:elevenlabs): fix exception in STT when serializing bool form field tag_audio_events by @mike-r-mclaughlin in #3282
primary speaker detection with STT diarization by @longcw in #3186
add capture_run for AgentSession.start by @longcw in #3288
chore: add test for empty tts streams by @davidzhao in #3286
fix say method not being captured by RunResult by @theomonnom in #3291
support interrupting agent by interim transcripts by @longcw in #3278
allow SpeechHandle to be interrupted when long-running function tools are pending by @longcw in #3280
fix: disable false interruption resume for realtime model by @longcw in #3298
feat(langgraph): support subgraphs in LLMAdapter and normalize astream outputs by @bnovik0v in #3112
feat: add more llm and stt models to mistralai plugins by @fabitokki in #3300
chore(langchain): fix types by @davidzhao in #3303

New Contributors

@bnovik0v made their first contribution in #3112

Full Changelog: https://github.com/livekit/agents/compare/[email protected]@1.2.8

Configuration

📅 Schedule: Branch creation - At any time (no schedule defined), Automerge - At any time (no schedule defined).

🚦 Automerge: Enabled.

♻ Rebasing: Whenever PR is behind base branch, or you tick the rebase/retry checkbox.

🔕 Ignore: Close this PR and you won't be reminded about these updates again.

If you want to rebase/retry this PR, check this box

This PR was generated by Mend Renovate. View the repository job log.

renovate bot force-pushed the renovate/livekit-dependencies-(non-major) branch from 0144c82 to c2b2ee1 Compare September 15, 2025 20:56

renovate bot changed the title ~~Update LiveKit dependencies (non-major) to v1.2.8~~ Update LiveKit dependencies (non-major) to v1.2.9 Sep 15, 2025

renovate bot force-pushed the renovate/livekit-dependencies-(non-major) branch from c2b2ee1 to 630b60c Compare September 18, 2025 21:07

renovate bot changed the title ~~Update LiveKit dependencies (non-major) to v1.2.9~~ Update LiveKit dependencies (non-major) to v1.2.11 Sep 18, 2025

renovate bot force-pushed the renovate/livekit-dependencies-(non-major) branch from 630b60c to 0b25c00 Compare September 29, 2025 05:13

renovate bot changed the title ~~Update LiveKit dependencies (non-major) to v1.2.11~~ Update LiveKit dependencies (non-major) to v1.2.12 Sep 29, 2025

renovate bot force-pushed the renovate/livekit-dependencies-(non-major) branch from 0b25c00 to 2960c42 Compare October 1, 2025 21:33

renovate bot changed the title ~~Update LiveKit dependencies (non-major) to v1.2.12~~ Update LiveKit dependencies (non-major) to v1.2.14 Oct 1, 2025

renovate bot force-pushed the renovate/livekit-dependencies-(non-major) branch from 2960c42 to 6ddfcd8 Compare October 15, 2025 20:28

renovate bot changed the title ~~Update LiveKit dependencies (non-major) to v1.2.14~~ Update LiveKit dependencies (non-major) to v1.2.15 Oct 15, 2025

renovate bot force-pushed the renovate/livekit-dependencies-(non-major) branch from 6ddfcd8 to fd4ed8f Compare October 27, 2025 12:42

renovate bot changed the title ~~Update LiveKit dependencies (non-major) to v1.2.15~~ Update LiveKit dependencies (non-major) to v1.2.16 Oct 27, 2025

renovate bot force-pushed the renovate/livekit-dependencies-(non-major) branch from fd4ed8f to b44e2bb Compare October 29, 2025 17:39

renovate bot changed the title ~~Update LiveKit dependencies (non-major) to v1.2.16~~ Update LiveKit dependencies (non-major) to v1.2.17 Oct 29, 2025

Update LiveKit dependencies (non-major) to v1.2.18

f1d182d

renovate bot force-pushed the renovate/livekit-dependencies-(non-major) branch from b44e2bb to f1d182d Compare November 5, 2025 21:08

renovate bot changed the title ~~Update LiveKit dependencies (non-major) to v1.2.17~~ Update LiveKit dependencies (non-major) to v1.2.18 Nov 5, 2025

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

Update LiveKit dependencies (non-major) to v1.2.18 #6

Update LiveKit dependencies (non-major) to v1.2.18 #6

Uh oh!

renovate bot commented Sep 2, 2025 •

edited

Loading

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

1 participant

Update LiveKit dependencies (non-major) to v1.2.18 #6

Are you sure you want to change the base?

Update LiveKit dependencies (non-major) to v1.2.18 #6

Uh oh!

Conversation

renovate bot commented Sep 2, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Release Notes

What's Changed

New Contributors

What's Changed

New Contributors

What's Changed

New Contributors

What's Changed

New Contributors

New feature

What's Changed

What's Changed

New Contributors

What's Changed

New Contributors

What's Changed

New Contributors

Features:

What's Changed

New Contributors

Features:

What's Changed

New Contributors

Configuration

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

1 participant

renovate bot commented Sep 2, 2025 •

edited

Loading