Skip to content

Commit 1cbe671

Browse files
sam-s10ssam-s10s
committed
Squashed commit of the following:
commit 829c5f4 Merge: e69ccd8 dc8ea61 Author: Mark Backman <mark@daily.co> Date: Sat Jan 17 16:25:12 2026 -0500 Merge pull request pipecat-ai#3169 from Incanta/hathora Add Hathora STT and TTS services commit dc8ea61 Author: Mike Seese <seesemichaelj@gmail.com> Date: Sat Jan 17 10:33:58 2026 -0800 add hathora to run-release-evals.py commit a3d2060 Author: Mike Seese <seesemichaelj@gmail.com> Date: Sat Jan 17 10:31:08 2026 -0800 move hathora example as requested commit f48a567 Author: Mike Seese <seesemichaelj@gmail.com> Date: Sat Jan 17 10:30:47 2026 -0800 run the linter commit e69ccd8 Merge: af89154 11924bb Author: Mark Backman <mark@daily.co> Date: Sat Jan 17 11:05:15 2026 -0500 Merge pull request pipecat-ai#3490 from pipecat-ai/mb/on-user-mute-events Add on_user_mute_started and on_user_mute_stopped events commit 11924bb Author: Mark Backman <mark@daily.co> Date: Sat Jan 17 10:10:58 2026 -0500 Add on_user_mute_started and on_user_mute_stopped events commit af89154 Merge: 1485ea0 e22bc77 Author: Mark Backman <mark@daily.co> Date: Sat Jan 17 11:00:30 2026 -0500 Merge pull request pipecat-ai#3489 from pipecat-ai/mb/fix-azure-tts-punctuation-spacing fix: AzureTTSService punctuation spacing commit 1485ea0 Merge: f7d3e63 1e11609 Author: Mark Backman <mark@daily.co> Date: Sat Jan 17 11:00:16 2026 -0500 Merge pull request pipecat-ai#3488 from pipecat-ai/mb/on-user-turn-idle Update on_user_idle to on_user_turn_idle commit e22bc77 Author: Mark Backman <mark@daily.co> Date: Sat Jan 17 09:04:50 2026 -0500 Fix spacing for CJK languages commit 043403f Author: Mark Backman <mark@daily.co> Date: Sat Jan 17 08:17:06 2026 -0500 fix: AzureTTSService punctuation spacing commit 1e11609 Author: Mark Backman <mark@daily.co> Date: Sat Jan 17 06:56:08 2026 -0500 Update on_user_idle to on_user_turn_idle commit f7d3e63 Merge: 473d397 1c13ad9 Author: Aleix Conchillo Flaqué <aleix@daily.co> Date: Fri Jan 16 22:06:45 2026 -0800 Merge pull request pipecat-ai#3474 from pipecat-ai/fix/optional-member-access-function-call-cancel Fix Pylance reportOptionalMemberAccess in _handle_function_call_cancel commit 473d397 Merge: 2114abb 2e8e574 Author: Mark Backman <mark@daily.co> Date: Fri Jan 16 18:47:10 2026 -0500 Merge pull request pipecat-ai#3482 from pipecat-ai/mb/user-idle-in-user-aggregator Add UserIdleController, deprecate UserIdleProcessor commit 2114abb Author: Aleix Conchillo Flaqué <aleix@daily.co> Date: Fri Jan 16 15:46:29 2026 -0800 add changelog file for 3484 commit 4fb4c26 Merge: 84c7e97 a6e7c99 Author: Aleix Conchillo Flaqué <aleix@daily.co> Date: Fri Jan 16 15:44:52 2026 -0800 Merge pull request pipecat-ai#3484 from amichyrpi/main Remove async_mode parameter from Mem0 storage commit 2e8e574 Author: Mark Backman <mark@daily.co> Date: Fri Jan 16 17:09:11 2026 -0500 Add UserIdleController, deprecate UserIdleProcessor commit 84c7e97 Merge: b11150f ac3fa7f Author: Aleix Conchillo Flaqué <aleix@daily.co> Date: Fri Jan 16 15:29:37 2026 -0800 Merge pull request pipecat-ai#3483 from pipecat-ai/aleix/throttle-user-speaking-frame throttle user speaking frame commit a6e7c99 Author: Amory Hen <214372542+amichyrpi@users.noreply.github.com> Date: Sat Jan 17 00:26:38 2026 +0100 Remove async_mode parameter from Mem0 storage commit ac3fa7f Author: Aleix Conchillo Flaqué <aleix@daily.co> Date: Fri Jan 16 14:46:25 2026 -0800 BaseOuputTransport: minor cleanup commit 6eadad5 Author: Aleix Conchillo Flaqué <aleix@daily.co> Date: Fri Jan 16 14:45:30 2026 -0800 BaseInputTransport: throttle UserSpeakingFrame commit b11150f Merge: 1e8516e 836cf60 Author: kompfner <paul@daily.co> Date: Fri Jan 16 15:46:27 2026 -0500 Merge pull request pipecat-ai#3480 from pipecat-ai/pk/fix-grok-realtime-smallwebrtc Fix an issue where Grok Realtime would error out when running with Sm… commit 836cf60 Author: Paul Kompfner <paul@daily.co> Date: Fri Jan 16 15:38:33 2026 -0500 Fix an issue where Grok Realtime would error out when running with SmallWebRTC transport. The underlying issue was related to the fact that we were sending audio to Grok before we had configured the Grok session with our default input sample rate (16000), so Grok was interpreting those initial audio chunks as having its default sample rate (24000). We didn't see this issue when using the Daily transport simply because in our test environments Daily took a smidge longer than a reflexive (localhost) pure WebRTC connection, so we would only send audio to Grok *after* we had configured the Grok session with the desired sample rate. commit 1c13ad9 Author: James Hush <james@daily.co> Date: Fri Jan 16 14:38:05 2026 +0800 Fix Pylance reportOptionalMemberAccess in _handle_function_call_cancel Extract dictionary value to local variable and check for None before accessing cancel_on_interruption attribute, since the dictionary values are typed as Optional[FunctionCallInProgressFrame]. commit 1e8516e Merge: 32c7753 11ecc5f Author: Mark Backman <mark@daily.co> Date: Fri Jan 16 14:57:39 2026 -0500 Merge pull request pipecat-ai#3476 from pipecat-ai/mb/project-urls Update project.urls for PyPI commit 32c7753 Merge: 28d0bb9 ec40696 Author: Mark Backman <mark@daily.co> Date: Fri Jan 16 14:57:24 2026 -0500 Merge pull request pipecat-ai#3471 from pipecat-ai/mb/fix-pydantic-2.12-docs Revert pydantic 2.12 extra type annotation commit 28d0bb9 Merge: a9a9f3a 63d1393 Author: Mark Backman <mark@daily.co> Date: Fri Jan 16 14:55:48 2026 -0500 Merge pull request pipecat-ai#3472 from pipecat-ai/mb/whisker-dev Add whisker_setup.py setup file to .gitignore commit a9a9f3a Merge: 41cb53f c2a0735 Author: Aleix Conchillo Flaqué <aleix@daily.co> Date: Fri Jan 16 11:18:23 2026 -0800 Merge pull request pipecat-ai#3462 from pipecat-ai/aleix/fix-min-words-transcription-aggregation MinWordsUserTurnStartStrategy: don't aggregate transcriptions commit c2a0735 Author: Aleix Conchillo Flaqué <aleix@daily.co> Date: Thu Jan 15 10:32:23 2026 -0800 MinWordsUserTurnStartStrategy: don't aggregate transcriptions If we aggregate transcriptions we will get incorrect interruptions. For example, if we have a strategy with min_words=3 and we say "One" and pause, then "Two" and pause and then "Three", this would trigger the start of the turn when it shouldn't. We should only look at the incoming transcription text and don't aggregate it with the previous. commit 41cb53f Merge: 19fb3ee 58552af Author: Aleix Conchillo Flaqué <aleix@daily.co> Date: Fri Jan 16 11:11:50 2026 -0800 Merge pull request pipecat-ai#3479 from pipecat-ai/aleix/turns-mute-to-user-mute turns: move mute to user_mute commit 58552af Author: Aleix Conchillo Flaqué <aleix@daily.co> Date: Fri Jan 16 10:58:34 2026 -0800 examples(foundational): remote STTMuteFilter example commit c7ab87b Author: Aleix Conchillo Flaqué <aleix@daily.co> Date: Fri Jan 16 10:52:23 2026 -0800 turns: move mute to user_mute commit 11ecc5f Author: Mark Backman <mark@daily.co> Date: Fri Jan 16 12:48:13 2026 -0500 Update project.urls for PyPI commit 19fb3ee Merge: b292b32 ce99924 Author: kompfner <paul@daily.co> Date: Fri Jan 16 09:56:13 2026 -0500 Merge pull request pipecat-ai#3466 from pipecat-ai/pk/fix-aws-nova-sonic-rtvi-bot-output Fix realtime (speech-to-speech) services' RTVI event compatibility commit b292b32 Merge: 64a1ad2 37914cb Author: Mark Backman <mark@daily.co> Date: Thu Jan 15 20:26:36 2026 -0500 Merge pull request pipecat-ai#3461 from glennpow/glenn/websocket-headers Allow WebsocketClientTransport to send custom headers commit 63d1393 Author: Mark Backman <mark@daily.co> Date: Thu Jan 15 20:06:49 2026 -0500 Add whisker_setup.py to .gitignore commit 37914cb Author: Glenn Powell <glennpow@gmail.com> Date: Thu Jan 15 16:47:15 2026 -0800 Removed import and added changelog entry. commit ec40696 Author: Mark Backman <mark@daily.co> Date: Thu Jan 15 19:16:15 2026 -0500 Revert pydantic 2.12 extra type annotation commit 2249f3d Author: Mike Seese <seesemichaelj@gmail.com> Date: Sat Jan 10 15:34:35 2026 -0800 add requested changes from code review commit d2df324 Author: Mike Seese <seesemichaelj@gmail.com> Date: Mon Jan 5 11:49:52 2026 -0800 fix some bugs after testing changes commit 67fdb0b Author: Mike Seese <seesemichaelj@gmail.com> Date: Mon Jan 5 11:15:43 2026 -0800 use parent _settings dict instead of self._params pattern commit e77bdf6 Author: Mike Seese <seesemichaelj@gmail.com> Date: Mon Jan 5 11:13:48 2026 -0800 add can_generate_metrics functions commit 1b3b677 Author: Mike Seese <seesemichaelj@gmail.com> Date: Mon Jan 5 10:57:27 2026 -0800 switch hathora services to use `InputParams` pattern commit 6c7e386 Author: Mike Seese <seesemichaelj@gmail.com> Date: Mon Jan 5 10:48:55 2026 -0800 remove traced_stt from run_stt commit ba25b27 Author: Mike Seese <seesemichaelj@gmail.com> Date: Mon Jan 5 10:38:11 2026 -0800 fix issues with PR suggestions commit e7c83c1 Author: Mike Seese <seesemichaelj@gmail.com> Date: Mon Jan 5 10:36:08 2026 -0800 port turn_start_strategies to the newer user_turn_strategies commit 7be7fb4 Author: Mike Seese <seesemichaelj@gmail.com> Date: Mon Jan 5 10:20:49 2026 -0800 remove turn_analyzer args from transport params commit bcccb4c Author: Mike Seese <seesemichaelj@gmail.com> Date: Mon Jan 5 10:20:26 2026 -0800 put fallback sample_rate value in function arg commit e9f1d95 Author: Mike Seese <seesemichaelj@gmail.com> Date: Mon Jan 5 10:16:06 2026 -0800 Apply suggestions from code review Co-authored-by: Mark Backman <m.backman@gmail.com> commit e5632a9 Author: Mike Seese <seesemichaelj@gmail.com> Date: Wed Dec 17 19:16:58 2025 -0800 transition Hathora service to use the unified API and apply PR feedback add Hathora to root files Hathora run linter added hathora changelog commit 1510fb4 Author: Mike Seese <seesemichaelj@gmail.com> Date: Mon Dec 1 15:01:06 2025 -0800 add Hathora STT and TTS services commit 64a1ad2 Merge: e75c241 4458ca1 Author: Mark Backman <mark@daily.co> Date: Thu Jan 15 17:34:44 2026 -0500 Merge pull request pipecat-ai#3470 from pipecat-ai/mb/fix-docs-0.0.99 Docs fixes after 0.0.99 commit 4458ca1 Author: Mark Backman <mark@daily.co> Date: Thu Jan 15 17:11:06 2026 -0500 Mock FastAPI commit 21aaa48 Author: Mark Backman <mark@daily.co> Date: Thu Jan 15 17:02:30 2026 -0500 Fix pydantic issues impacting autodoc commit e75c241 Merge: c8e4b46 f3c2e29 Author: Mark Backman <mark@daily.co> Date: Thu Jan 15 17:16:28 2026 -0500 Merge pull request pipecat-ai#3468 from pipecat-ai/mb/camb-cleanuo Clean up CambTTSService commit 6021604 Author: Mark Backman <mark@daily.co> Date: Thu Jan 15 16:22:17 2026 -0500 Docs fixes after 0.0.99 commit f3c2e29 Author: Mark Backman <mark@daily.co> Date: Thu Jan 15 15:59:17 2026 -0500 Clean up CambTTSService commit ce99924 Author: Paul Kompfner <paul@daily.co> Date: Thu Jan 15 15:55:22 2026 -0500 Add CHANGELOG entry describing fix for the missing "bot-llm-text" RTVI event when using realtime (speech-to-speech) services commit 5de80a6 Author: Paul Kompfner <paul@daily.co> Date: Thu Jan 15 15:30:00 2026 -0500 Fix "bot-llm-text" not firing when using Grok Realtime commit 5753762 Author: Paul Kompfner <paul@daily.co> Date: Thu Jan 15 15:16:08 2026 -0500 Fix "bot-llm-text" not firing when using OpenAI Realtime commit 885b318 Author: Paul Kompfner <paul@daily.co> Date: Thu Jan 15 15:03:45 2026 -0500 Fix "bot-llm-text" not firing when using Gemini Live commit 7a22d58 Author: Paul Kompfner <paul@daily.co> Date: Thu Jan 15 14:48:39 2026 -0500 Fix "bot-llm-text" not firing when using AWS Nova Sonic commit c8e4b46 Merge: 30a3f42 efd4432 Author: Mark Backman <mark@daily.co> Date: Thu Jan 15 14:44:21 2026 -0500 Merge pull request pipecat-ai#3460 from pipecat-ai/mb/reorder-07-examples Renumber the 07 foundational examples commit 30a3f42 Merge: 24082b8 26ddb2d Author: Mark Backman <mark@daily.co> Date: Thu Jan 15 14:43:12 2026 -0500 Merge pull request pipecat-ai#3349 from eRuaro/feat/camb-tts-integration Add Camb.ai TTS integration with MARS models commit 26ddb2d Author: Neil Ruaro <neil.ruaro@intellecs.ai> Date: Fri Jan 16 03:18:01 2026 +0800 minimal uv.lock update for camb-sdk commit f60eeaa Author: Neil Ruaro <neil.ruaro@intellecs.ai> Date: Fri Jan 16 02:50:18 2026 +0800 reverted uv.lock, updated readthedocs.yaml, copyright year updates commit 8cf72b3 Author: Neil Ruaro <neil.ruaro@intellecs.ai> Date: Fri Jan 16 02:26:38 2026 +0800 manually add camb-sdk to uv.lock, exclude camb from docs build commit 38c3bce Author: Neil Ruaro <neil.ruaro@intellecs.ai> Date: Fri Jan 16 02:20:26 2026 +0800 exclude camb from docs build commit 80604ba Author: Neil Ruaro <neil.ruaro@intellecs.ai> Date: Fri Jan 16 02:00:48 2026 +0800 remove _update_settings method commit 256c70c Author: Neil Ruaro <neil.ruaro@intellecs.ai> Date: Fri Jan 16 01:32:08 2026 +0800 use UserTurnStrategies commit 0e3532c Author: Glenn Powell <glennpow@gmail.com> Date: Thu Jan 15 09:31:48 2026 -0800 Allow WebsocketClientTransport to send custom headers commit 9942fcf Author: Neil Ruaro <neil.ruaro@intellecs.ai> Date: Fri Jan 16 01:15:46 2026 +0800 updated per PR reviews commit 003c24c Author: Neil Ruaro <neil.ruaro@intellecs.ai> Date: Tue Jan 13 07:06:31 2026 +0900 Make model parameter explicit in docstring example commit ed120d0 Author: Neil Ruaro <neil.ruaro@intellecs.ai> Date: Tue Jan 13 06:32:11 2026 +0900 Add model-specific sample rates, transport example, and fix audio buffer alignment commit e76a3d0 Author: Neil Ruaro <neil.ruaro@intellecs.ai> Date: Tue Jan 13 00:43:46 2026 +0900 Update Camb TTS to 48kHz sample rate commit 641d170 Author: Neil Ruaro <neil.ruaro@intellecs.ai> Date: Mon Jan 12 22:20:42 2026 +0900 Clean up Camb TTS service and tests commit 9293b5f Author: Neil Ruaro <neil.ruaro@intellecs.ai> Date: Mon Jan 12 19:23:43 2026 +0900 Migrate Camb TTS service from raw HTTP to official SDK - Replace aiohttp with camb SDK (AsyncCambAI client) - Add support for passing existing SDK client instance - Simplify API: no longer requires aiohttp_session parameter - Update example to use simplified initialization - Rewrite tests to mock SDK client instead of HTTP servers commit c1f3cbd Author: Neil Ruaro <neil.ruaro@intellecs.ai> Date: Mon Jan 12 17:51:38 2026 +0900 Yield TTSAudioRawFrame directly instead of calling private method commit 78fa2ab Author: Neil Ruaro <neil.ruaro@intellecs.ai> Date: Fri Jan 9 21:22:33 2026 +0900 Update default voice ID, fix MARS naming, and clean up example commit 56da2ca Author: Neil Ruaro <neil.ruaro@intellecs.ai> Date: Fri Jan 9 18:30:38 2026 +0900 Update Camb.ai TTS inference options commit a541d65 Author: Neil Ruaro <neil.ruaro@intellecs.ai> Date: Fri Jan 9 18:20:50 2026 +0900 Update MARS model names to mars-flash, mars-pro, mars-instruct Rename model identifiers from mars-8-* to the new naming convention: - mars-8-flash -> mars-flash (default) - mars-8 -> removed - mars-8-instruct -> mars-instruct - Added mars-pro commit a3d7e9e Author: Neil Ruaro <neil.ruaro@intellecs.ai> Date: Mon Jan 5 20:34:05 2026 +0800 Address PR feedback: add --voice-id arg, remove test script - Add --voice-id CLI argument to example (default: 2681) - Remove test_camb_quick.py from examples/ (tests belong in tests/) - Update docstring with new usage commit 54933be Author: Neil Ruaro <neil.ruaro@intellecs.ai> Date: Mon Jan 5 06:07:12 2026 +0800 Rename changelog to PR number commit fcab989 Author: Neil Ruaro <neil.ruaro@intellecs.ai> Date: Mon Jan 5 05:53:46 2026 +0800 Add changelog entry for Camb.ai TTS integration commit be098e8 Author: Neil Ruaro <neil.ruaro@intellecs.ai> Date: Mon Jan 5 05:35:31 2026 +0800 Remove non-working Daily/WebRTC example The Daily transport example had authentication issues. Keeping the local audio example (07zb-interruptible-camb-local.py) which works. commit ed0ff46 Author: Neil Ruaro <neil.ruaro@intellecs.ai> Date: Sun Jan 4 22:20:02 2026 +0800 added local test commit 7ae0d65 Author: Neil Ruaro <neil.ruaro@intellecs.ai> Date: Mon Dec 29 21:08:40 2025 +0800 added cambai tts integration commit efd4432 Author: Mark Backman <mark@daily.co> Date: Thu Jan 15 10:24:09 2026 -0500 Renumber the 07 foundational examples commit 24082b8 Merge: dcd5840 e107902 Author: kompfner <paul@daily.co> Date: Thu Jan 15 09:24:14 2026 -0500 Merge pull request pipecat-ai#3453 from pipecat-ai/pk/consistency-pass-on-user-started-stopped-speaking-frames Do a consistency pass on how we're sending `UserStartedSpeakingFrame`… commit dcd5840 Merge: 965466c 9e705ce Author: Aleix Conchillo Flaqué <aleix@daily.co> Date: Wed Jan 14 19:28:32 2026 -0800 Merge pull request pipecat-ai#3455 from pipecat-ai/aleix/reset-user-turn-start-strategies UserTurnController: reset user turn start strategies when turn triggered commit 9e705ce Author: Aleix Conchillo Flaqué <aleix@daily.co> Date: Wed Jan 14 17:50:31 2026 -0800 UserTurnController: reset user turn start strategies when turn triggered commit 965466c Merge: e7b5ff4 f3993f1 Author: Mark Backman <mark@daily.co> Date: Wed Jan 14 20:15:31 2026 -0500 Merge pull request pipecat-ai#3454 from pipecat-ai/mb/external-turn-strategies-timeout fix to make on_user_turn_stop_timeout work with ExternalUserTurnStrat… commit f3993f1 Author: Mark Backman <mark@daily.co> Date: Wed Jan 14 20:01:50 2026 -0500 fix to make on_user_turn_stop_timeout work with ExternalUserTurnStrategies commit e107902 Author: Paul Kompfner <paul@daily.co> Date: Wed Jan 14 18:40:07 2026 -0500 Do a consistency pass on how we're sending `UserStartedSpeakingFrame`s and `UserStoppedSpeakingFrame`s. The codebase is now consistent in broadcasting both types of frames up and downstream. commit e7b5ff4 Merge: 3d858e8 e33172c Author: kompfner <paul@daily.co> Date: Wed Jan 14 15:33:44 2026 -0500 Merge pull request pipecat-ai#3447 from pipecat-ai/pk/add-pr-3420-to-changelog Add PR 3420 to CHANGELOG (it was missing) commit e33172c Author: Paul Kompfner <paul@daily.co> Date: Wed Jan 14 11:04:24 2026 -0500 Add PR 3420 to CHANGELOG (it was missing) commit 3d858e8 Merge: eab059c cb364f3 Author: Mark Backman <mark@daily.co> Date: Wed Jan 14 10:29:55 2026 -0500 Merge pull request pipecat-ai#3444 from pipecat-ai/mb/update-quickstart-0.0.99 Update quickstart example for 0.0.99 commit eab059c Merge: a9bfb09 4aaff04 Author: Mark Backman <mark@daily.co> Date: Wed Jan 14 10:28:57 2026 -0500 Merge pull request pipecat-ai#3446 from pipecat-ai/mb/add-3392-changelog Add PR 3392 to changelog, linting cleanup commit 4aaff04 Author: Mark Backman <mark@daily.co> Date: Wed Jan 14 09:43:17 2026 -0500 Add PR 3392 to changelog, linting cleanup commit cb364f3 Author: Mark Backman <mark@daily.co> Date: Wed Jan 14 08:58:04 2026 -0500 Update quickstart example for 0.0.99 commit a9bfb09 Merge: 86ed485 c4ae402 Author: Mark Backman <mark@daily.co> Date: Wed Jan 14 07:52:52 2026 -0500 Merge pull request pipecat-ai#3287 from ashotbagh/feature/asyncai-multicontext-wss Fix TTFB metric and add multi-context WebSocket support for Async TTS commit c4ae402 Author: Ashot <ashot.baghdasaryan@podcastle.ai> Date: Wed Jan 14 16:33:30 2026 +0400 Adjustments of Async TTS for multicontext websocket support commit 15067c6 Author: Ashot <ashot.baghdasaryan@podcastle.ai> Date: Wed Jan 7 21:42:30 2026 +0400 adapt Async TTS to updated AudioContextTTSService commit 5ae592f Author: Ashot <ashot.baghdasaryan@podcastle.ai> Date: Wed Jan 7 15:55:35 2026 +0400 Improve Async TTS interruption handling by using AudioContextTTSService class and add changelog fragments commit 9cdbc56 Author: Ashot <ashot.baghdasaryan@podcastle.ai> Date: Tue Dec 23 16:35:45 2025 +0400 Fix TTFB metric and add multi-context WebSocket support for Async TTS commit 86ed485 Merge: 6fd5847 7e1b4a4 Author: Aleix Conchillo Flaqué <aleix@daily.co> Date: Tue Jan 13 17:02:41 2026 -0800 Merge pull request pipecat-ai#3440 from pipecat-ai/changelog-0.0.99 Release 0.0.99 - Changelog Update commit 7e1b4a4 Author: Aleix Conchillo Flaqué <aleix@daily.co> Date: Tue Jan 13 16:59:46 2026 -0800 update cosmetic changelog updates for 0.0.99 commit 4531d51 Author: aconchillo <951761+aconchillo@users.noreply.github.com> Date: Wed Jan 14 00:49:15 2026 +0000 Update changelog for version 0.0.99 commit 6fd5847 Merge: 84f16ee 2015eba Author: Aleix Conchillo Flaqué <aleix@daily.co> Date: Tue Jan 13 16:48:07 2026 -0800 Merge pull request pipecat-ai#3439 from pipecat-ai/aleix/uv-lock-2026-01-13 uv.lock: upgrade to latest versions commit 2015eba Author: Aleix Conchillo Flaqué <aleix@daily.co> Date: Tue Jan 13 16:45:44 2026 -0800 uv.lock: upgrade to latest versions commit 84f16ee Merge: 5b2af03 b313395 Author: Mark Backman <mark@daily.co> Date: Tue Jan 13 19:43:50 2026 -0500 Merge pull request pipecat-ai#3438 from pipecat-ai/mb/fix-26a Fix 26a foundational commit 5b2af03 Merge: 248dac3 0d6bdbe Author: Aleix Conchillo Flaqué <aleix@daily.co> Date: Tue Jan 13 16:39:29 2026 -0800 Merge pull request pipecat-ai#3437 from pipecat-ai/aleix/update-aggregator-logs LLMContextAggregatorPair: make strategy logs less verbose commit b313395 Author: Mark Backman <mark@daily.co> Date: Tue Jan 13 19:31:24 2026 -0500 Fix 26a foundational commit 0d6bdbe Author: Aleix Conchillo Flaqué <aleix@daily.co> Date: Tue Jan 13 15:11:22 2026 -0800 LLMContextAggregatorPair: make strategy logs less verbose commit 248dac3 Merge: bd9ee0d be49a54 Author: Aleix Conchillo Flaqué <aleix@daily.co> Date: Tue Jan 13 14:40:33 2026 -0800 Merge pull request pipecat-ai#3420 from pipecat-ai/pk/fix-gemini-3-parallel-function-calls Fix parallel function calling with Gemini 3. commit be49a54 Author: Paul Kompfner <paul@daily.co> Date: Tue Jan 13 17:32:20 2026 -0500 Fast-exit in the fix for parallel function calling with Gemini 3, if we can determine up-front that there's no work to do commit bd9ee0d Merge: 442e0e5 ee82377 Author: Aleix Conchillo Flaqué <aleix@daily.co> Date: Tue Jan 13 14:12:51 2026 -0800 Merge pull request pipecat-ai#3434 from pipecat-ai/aleix/context-appregator-pair-tuple context aggregator pair tuple commit 442e0e5 Merge: 38194c0 bb00d22 Author: Mark Backman <mark@daily.co> Date: Tue Jan 13 17:10:40 2026 -0500 Merge pull request pipecat-ai#3431 from pipecat-ai/mb/update-realtime-examples-transcript-handler Update GeminiLiveLLMService to push thought frames, update 26a for new transcript events commit 38194c0 Merge: 86fbfad 0ebdaba Author: kompfner <paul@daily.co> Date: Tue Jan 13 17:06:17 2026 -0500 Merge pull request pipecat-ai#3436 from pipecat-ai/pk/remove-transcript-processor-reference Remove dead import of `TranscriptProcessor` (which is now deprecated) commit 0ebdaba Author: Paul Kompfner <paul@daily.co> Date: Tue Jan 13 17:02:57 2026 -0500 Remove dead import of `TranscriptProcessor` (which is now deprecated) commit ee82377 Author: Aleix Conchillo Flaqué <aleix@daily.co> Date: Tue Jan 13 13:40:24 2026 -0800 examples: fix 22d to push some CancelFrame and EndFrame commit 861588e Author: Aleix Conchillo Flaqué <aleix@daily.co> Date: Tue Jan 13 13:40:03 2026 -0800 examples: update all examples to use the new LLMContextAggregatorPair tuple commit 1ab3bf2 Author: Aleix Conchillo Flaqué <aleix@daily.co> Date: Tue Jan 13 13:40:55 2026 -0800 LLMContextAggregatorPair: instances can now return a tuple commit bb00d22 Author: Mark Backman <mark@daily.co> Date: Tue Jan 13 14:13:32 2026 -0500 Update 26a to use context aggregator transcription events commit 86fbfad Merge: 87d0dc9 5612bf5 Author: Aleix Conchillo Flaqué <aleix@daily.co> Date: Tue Jan 13 13:59:28 2026 -0800 Merge pull request pipecat-ai#3435 from pipecat-ai/aleix/fix-llm-context-create-audio-message LLMContext: fix create_audio_message commit 5612bf5 Author: Aleix Conchillo Flaqué <aleix@daily.co> Date: Tue Jan 13 13:50:09 2026 -0800 LLMContext: fix create_audio_message commit 87d0dc9 Merge: 5d90f4e 89484e2 Author: Mark Backman <mark@daily.co> Date: Tue Jan 13 16:45:26 2026 -0500 Merge pull request pipecat-ai#3412 from pipecat-ai/mb/remove-41a-b Remove foundational examples 41a and 41b commit 30fbcfb Author: Paul Kompfner <paul@daily.co> Date: Tue Jan 13 16:33:59 2026 -0500 Rework fix for parallel function calling with Gemini 3 commit 5d90f4e Merge: f6d09e1 efbc0c8 Author: Mark Backman <mark@daily.co> Date: Tue Jan 13 15:40:10 2026 -0500 Merge pull request pipecat-ai#3428 from pipecat-ai/mb/fix-tracing-none-values Fix TTS, realtime LLM services could return unknown for model_name commit f6d09e1 Merge: b8e48de 21534f7 Author: kompfner <paul@daily.co> Date: Tue Jan 13 15:36:44 2026 -0500 Merge pull request pipecat-ai#3430 from pipecat-ai/pk/request-image-frame-fixes Fix request_image_frame and usage commit b8e48de Merge: a6ccb9e d591f9e Author: Mark Backman <mark@daily.co> Date: Tue Jan 13 15:36:06 2026 -0500 Merge pull request pipecat-ai#3433 from pipecat-ai/mb/port-realtime-examples-transcript-events Update examples to use transcription events from context aggregators commit a6ccb9e Merge: 66551eb 41eef5e Author: Mark Backman <mark@daily.co> Date: Tue Jan 13 15:35:24 2026 -0500 Merge pull request pipecat-ai#3427 from pipecat-ai/mb/add-07j-gladia-vad-example Add 07j Gladia VAD foundational example, add to release evals commit 66551eb Merge: d0f2271 f00f9d9 Author: Mark Backman <mark@daily.co> Date: Tue Jan 13 15:34:58 2026 -0500 Merge pull request pipecat-ai#3426 from pipecat-ai/mb/changelog-3404 Add changelog fragments for PR 3404 commit 21534f7 Author: Aleix Conchillo Flaqué <aleix@daily.co> Date: Tue Jan 13 12:21:22 2026 -0800 added changelog file for pipecat-ai#3430 commit d591f9e Author: Mark Backman <mark@daily.co> Date: Tue Jan 13 15:20:59 2026 -0500 Remove 28-transcription-processor.py commit aa2589d Author: Mark Backman <mark@daily.co> Date: Tue Jan 13 15:13:05 2026 -0500 Update examples to use transcription events from context aggregators commit 9d6067f Author: Aleix Conchillo Flaqué <aleix@daily.co> Date: Tue Jan 13 12:07:11 2026 -0800 examples(foundational): speak "Let me check on that" in 14d examples commit 027e544 Author: Aleix Conchillo Flaqué <aleix@daily.co> Date: Tue Jan 13 11:57:12 2026 -0800 examples(foundational): associate image requests to function calls commit e268c73 Author: Aleix Conchillo Flaqué <aleix@daily.co> Date: Tue Jan 13 11:56:43 2026 -0800 LLMAssistantAggregator: cache function call requested images commit d3c57e2 Author: Aleix Conchillo Flaqué <aleix@daily.co> Date: Tue Jan 13 11:56:13 2026 -0800 UserImageRawFrame: don't deprecate request field commit 02eace5 Author: Aleix Conchillo Flaqué <aleix@daily.co> Date: Tue Jan 13 11:55:55 2026 -0800 UserImageRequestFrame: don't deprecate function call related fields commit 15bc1dd Author: Mark Backman <mark@daily.co> Date: Tue Jan 13 14:13:00 2026 -0500 Update GeminiLiveLLMService to push Thought frames when thought content is returned commit b937956 Author: Paul Kompfner <paul@daily.co> Date: Tue Jan 13 13:15:32 2026 -0500 Fix request_image_frame and usage commit efbc0c8 Author: Mark Backman <mark@daily.co> Date: Tue Jan 13 12:04:15 2026 -0500 Fix TTS, realtime LLM services could return unknown for model_name commit d0f2271 Author: Himanshu Gunwant <69423776+monster-anshu@users.noreply.github.com> Date: Tue Jan 13 22:25:52 2026 +0530 fix: openai llm model name is unknown (pipecat-ai#3422) commit 41eef5e Author: Mark Backman <mark@daily.co> Date: Tue Jan 13 11:36:15 2026 -0500 Add 07j Gladia VAD foundational example, add to release evals commit f00f9d9 Author: Mark Backman <mark@daily.co> Date: Tue Jan 13 11:29:17 2026 -0500 Add changelog fragments for PR 3404 commit ae59b3b Merge: 8b0f0b5 3304b18 Author: Mark Backman <mark@daily.co> Date: Tue Jan 13 11:26:56 2026 -0500 Merge pull request pipecat-ai#3404 from poseneror/feature/gladia-vad-events feat(gladia): add VAD events support commit 6668712 Author: Paul Kompfner <paul@daily.co> Date: Mon Jan 12 17:00:13 2026 -0500 Add evals for parallel function calling commit 8812686 Author: Paul Kompfner <paul@daily.co> Date: Mon Jan 12 16:01:48 2026 -0500 Fix parallel function calling with Gemini 3. Gemini expects parallel function calls to be passed in as a single multi-part `Content` block. This is important because only one of the function calls in a batch of parallel function calls gets a thought signature—if they're passed in as separate `Content` blocks, there'd be one or more missing thought signatures, which would result in a Gemini error. commit 8b0f0b5 Merge: a298ce3 f5e8a04 Author: kompfner <paul@daily.co> Date: Tue Jan 13 11:02:53 2026 -0500 Merge pull request pipecat-ai#3425 from pipecat-ai/pk/gemini-3-flash-new-thinking-levels Add Gemini 3 Flash-specific thinking levels commit f5e8a04 Author: Paul Kompfner <paul@daily.co> Date: Tue Jan 13 10:50:08 2026 -0500 Bump `aiortc` dependency, which relaxes the constraint on `av`, which was pinned to 14.4.0, which no longer has all necessary wheels commit a298ce3 Merge: f6ed7d7 31daa88 Author: Mark Backman <mark@daily.co> Date: Tue Jan 13 10:42:40 2026 -0500 Merge pull request pipecat-ai#3424 from pipecat-ai/mb/tts-append-trailing-space Add append_trailing_space to TTSService to prevent vocalizing trailin… commit 31daa88 Author: Mark Backman <mark@daily.co> Date: Tue Jan 13 09:24:23 2026 -0500 Add append_trailing_space to TTSService to prevent vocalizing trailing punctuation; update DeepgramTTSService and RimeTTSService to use the arg commit 76a0581 Author: Paul Kompfner <paul@daily.co> Date: Tue Jan 13 09:50:59 2026 -0500 Add Gemini 3 Flash-specific thinking levels commit 3304b18 Author: poseneror <posener.or@gmail.com> Date: Tue Jan 13 14:19:50 2026 +0200 Add should_interrupt + broadcast user events commit b95a6af Author: poseneror <posener.or@gmail.com> Date: Sun Jan 11 09:43:02 2026 +0200 feat(gladia): add VAD events support Add support for Gladia's speech_start/speech_end events to emit UserStartedSpeakingFrame and UserStoppedSpeakingFrame frames. When enable_vad=True in GladiaInputParams: - speech_start triggers interruption and pushes UserStartedSpeakingFrame - speech_end pushes UserStoppedSpeakingFrame - Tracks speaking state to prevent duplicate events This allows using Gladia's built-in VAD instead of a separate VAD in the pipeline. commit f6ed7d7 Merge: 2296caf cd3290d Author: Mark Backman <mark@daily.co> Date: Mon Jan 12 19:24:56 2026 -0500 Merge pull request pipecat-ai#3418 from pipecat-ai/mb/speechmatics-task-cleanup commit cd3290d Author: Mark Backman <mark@daily.co> Date: Mon Jan 12 16:00:32 2026 -0500 Small cleanup for task creation in SpeechmaticsSTTService commit 2296caf Merge: 90ded66 b58471f Author: Mark Backman <mark@daily.co> Date: Mon Jan 12 13:43:42 2026 -0500 Merge pull request pipecat-ai#3414 from pipecat-ai/mb/changelog-3410 Update changelog for PR 3410.changed.md commit 90ded66 Merge: 7e97fb8 aac24ad Author: Mark Backman <mark@daily.co> Date: Mon Jan 12 13:31:24 2026 -0500 Merge pull request pipecat-ai#3403 from pipecat-ai/mb/inworld-tts-add-keepalive InworldTTSService: Add keepalive task commit 7e97fb8 Merge: 46b4f9f f58d218 Author: Mark Backman <mark@daily.co> Date: Mon Jan 12 13:11:43 2026 -0500 Merge pull request pipecat-ai#3392 from pipecat-ai/mb/websocket-service-connection-closed-error Add reconnect logic to WebsocketService in the event of ConnectionClo… commit b58471f Author: Mark Backman <mark@daily.co> Date: Mon Jan 12 12:24:56 2026 -0500 Add Exotel and Vonage to Serializers in README services list commit 46b4f9f Merge: 2f429a2 ec20d72 Author: Aleix Conchillo Flaqué <aleix@daily.co> Date: Mon Jan 12 09:21:42 2026 -0800 Merge pull request pipecat-ai#3413 from pipecat-ai/aleix/fix-assistant-thought-aggregation LLMAssistantAggregator: reset aggregation after adding the thought, not before commit ec20d72 Author: Aleix Conchillo Flaqué <aleix@daily.co> Date: Mon Jan 12 09:07:23 2026 -0800 LLMAssistantAggregator: reset aggregation after adding the thought, not before commit 5743e2a Author: Mark Backman <mark@daily.co> Date: Mon Jan 12 12:15:40 2026 -0500 Update changelog for PR 3410.changed.md commit 2f429a2 Merge: 1df9575 3e982f7 Author: Mark Backman <mark@daily.co> Date: Mon Jan 12 12:10:57 2026 -0500 Merge pull request pipecat-ai#3410 from Vonage/feat/fastapi-ws-vonage-serializer feat: update FastAPI WebSocket transport and add Vonage serializer commit 3e982f7 Author: Varun Pratap Singh <varun.singh@vonage.com> Date: Mon Jan 12 22:11:39 2026 +0530 refactor: rename audio_packet_bytes to fixed_audio_packet_size commit 89484e2 Author: Mark Backman <mark@daily.co> Date: Mon Jan 12 10:11:58 2026 -0500 Remove foundational examples 41a and 41b commit 14a115f Author: Varun Pratap Singh <varun.singh@vonage.com> Date: Mon Jan 12 18:12:27 2026 +0530 changelog: add fragments for PR pipecat-ai#3410 commit e96595f Author: Varun Pratap Singh <varun.singh@vonage.com> Date: Mon Jan 12 17:50:38 2026 +0530 feat: update FastAPI WebSocket transport and add Vonage serializer commit f58d218 Author: Mark Backman <mark@daily.co> Date: Sun Jan 11 16:43:37 2026 -0500 WebsocketService: Add _maybe_try_reconnect and use for exception cases commit aac24ad Author: Mark Backman <mark@daily.co> Date: Sat Jan 10 11:18:35 2026 -0500 InworldTTSService: Add keepalive task commit 9c81acb Author: Mark Backman <mark@daily.co> Date: Fri Jan 9 16:48:51 2026 -0500 Track websocket disconnecting status to improve error handling commit 4fe0836 Author: Mark Backman <mark@daily.co> Date: Fri Jan 9 09:00:36 2026 -0500 Add reconnect logic to WebsocketService in the event of ConnectionClosedError
1 parent 2ac4498 commit 1cbe671

84 files changed

Lines changed: 1976 additions & 261 deletions

File tree

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

‎.gitignore‎

Lines changed: 4 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -51,4 +51,7 @@ docs/api/_build/
5151
docs/api/api
5252

5353
# uv
54-
.python-version
54+
.python-version
55+
56+
# Pipecat
57+
whisker_setup.py

‎README.md‎

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -73,9 +73,9 @@ Catch new features, interviews, and how-tos on our [Pipecat TV](https://www.yout
7373

7474
| Category | Services |
7575
| ------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
76-
| Speech-to-Text | [AssemblyAI](https://docs.pipecat.ai/server/services/stt/assemblyai), [AWS](https://docs.pipecat.ai/server/services/stt/aws), [Azure](https://docs.pipecat.ai/server/services/stt/azure), [Cartesia](https://docs.pipecat.ai/server/services/stt/cartesia), [Deepgram](https://docs.pipecat.ai/server/services/stt/deepgram), [ElevenLabs](https://docs.pipecat.ai/server/services/stt/elevenlabs), [Fal Wizper](https://docs.pipecat.ai/server/services/stt/fal), [Gladia](https://docs.pipecat.ai/server/services/stt/gladia), [Google](https://docs.pipecat.ai/server/services/stt/google), [Gradium](https://docs.pipecat.ai/server/services/stt/gradium), [Groq (Whisper)](https://docs.pipecat.ai/server/services/stt/groq), [NVIDIA Riva](https://docs.pipecat.ai/server/services/stt/riva), [OpenAI (Whisper)](https://docs.pipecat.ai/server/services/stt/openai), [SambaNova (Whisper)](https://docs.pipecat.ai/server/services/stt/sambanova), [Sarvam](https://docs.pipecat.ai/server/services/stt/sarvam), [Soniox](https://docs.pipecat.ai/server/services/stt/soniox), [Speechmatics](https://docs.pipecat.ai/server/services/stt/speechmatics), [Whisper](https://docs.pipecat.ai/server/services/stt/whisper) |
76+
| Speech-to-Text | [AssemblyAI](https://docs.pipecat.ai/server/services/stt/assemblyai), [AWS](https://docs.pipecat.ai/server/services/stt/aws), [Azure](https://docs.pipecat.ai/server/services/stt/azure), [Cartesia](https://docs.pipecat.ai/server/services/stt/cartesia), [Deepgram](https://docs.pipecat.ai/server/services/stt/deepgram), [ElevenLabs](https://docs.pipecat.ai/server/services/stt/elevenlabs), [Fal Wizper](https://docs.pipecat.ai/server/services/stt/fal), [Gladia](https://docs.pipecat.ai/server/services/stt/gladia), [Google](https://docs.pipecat.ai/server/services/stt/google), [Gradium](https://docs.pipecat.ai/server/services/stt/gradium), [Groq (Whisper)](https://docs.pipecat.ai/server/services/stt/groq), [Hathora](https://docs.pipecat.ai/server/services/stt/hathora), [NVIDIA Riva](https://docs.pipecat.ai/server/services/stt/riva), [OpenAI (Whisper)](https://docs.pipecat.ai/server/services/stt/openai), [SambaNova (Whisper)](https://docs.pipecat.ai/server/services/stt/sambanova), [Sarvam](https://docs.pipecat.ai/server/services/stt/sarvam), [Soniox](https://docs.pipecat.ai/server/services/stt/soniox), [Speechmatics](https://docs.pipecat.ai/server/services/stt/speechmatics), [Whisper](https://docs.pipecat.ai/server/services/stt/whisper) |
7777
| LLMs | [Anthropic](https://docs.pipecat.ai/server/services/llm/anthropic), [AWS](https://docs.pipecat.ai/server/services/llm/aws), [Azure](https://docs.pipecat.ai/server/services/llm/azure), [Cerebras](https://docs.pipecat.ai/server/services/llm/cerebras), [DeepSeek](https://docs.pipecat.ai/server/services/llm/deepseek), [Fireworks AI](https://docs.pipecat.ai/server/services/llm/fireworks), [Gemini](https://docs.pipecat.ai/server/services/llm/gemini), [Grok](https://docs.pipecat.ai/server/services/llm/grok), [Groq](https://docs.pipecat.ai/server/services/llm/groq), [Mistral](https://docs.pipecat.ai/server/services/llm/mistral), [NVIDIA NIM](https://docs.pipecat.ai/server/services/llm/nim), [Ollama](https://docs.pipecat.ai/server/services/llm/ollama), [OpenAI](https://docs.pipecat.ai/server/services/llm/openai), [OpenRouter](https://docs.pipecat.ai/server/services/llm/openrouter), [Perplexity](https://docs.pipecat.ai/server/services/llm/perplexity), [Qwen](https://docs.pipecat.ai/server/services/llm/qwen), [SambaNova](https://docs.pipecat.ai/server/services/llm/sambanova) [Together AI](https://docs.pipecat.ai/server/services/llm/together) |
78-
| Text-to-Speech | [Async](https://docs.pipecat.ai/server/services/tts/asyncai), [AWS](https://docs.pipecat.ai/server/services/tts/aws), [Azure](https://docs.pipecat.ai/server/services/tts/azure), [Cartesia](https://docs.pipecat.ai/server/services/tts/cartesia), [Deepgram](https://docs.pipecat.ai/server/services/tts/deepgram), [ElevenLabs](https://docs.pipecat.ai/server/services/tts/elevenlabs), [Fish](https://docs.pipecat.ai/server/services/tts/fish), [Google](https://docs.pipecat.ai/server/services/tts/google), [Gradium](https://docs.pipecat.ai/server/services/tts/gradium), [Groq](https://docs.pipecat.ai/server/services/tts/groq), [Hume](https://docs.pipecat.ai/server/services/tts/hume), [Inworld](https://docs.pipecat.ai/server/services/tts/inworld), [LMNT](https://docs.pipecat.ai/server/services/tts/lmnt), [MiniMax](https://docs.pipecat.ai/server/services/tts/minimax), [Neuphonic](https://docs.pipecat.ai/server/services/tts/neuphonic), [NVIDIA Riva](https://docs.pipecat.ai/server/services/tts/riva), [OpenAI](https://docs.pipecat.ai/server/services/tts/openai), [Piper](https://docs.pipecat.ai/server/services/tts/piper), [PlayHT](https://docs.pipecat.ai/server/services/tts/playht), [Rime](https://docs.pipecat.ai/server/services/tts/rime), [Sarvam](https://docs.pipecat.ai/server/services/tts/sarvam), [Speechmatics](https://docs.pipecat.ai/server/services/tts/speechmatics), [XTTS](https://docs.pipecat.ai/server/services/tts/xtts) |
78+
| Text-to-Speech | [Async](https://docs.pipecat.ai/server/services/tts/asyncai), [AWS](https://docs.pipecat.ai/server/services/tts/aws), [Azure](https://docs.pipecat.ai/server/services/tts/azure), [Camb AI](https://docs.pipecat.ai/server/services/tts/camb), [Cartesia](https://docs.pipecat.ai/server/services/tts/cartesia), [Deepgram](https://docs.pipecat.ai/server/services/tts/deepgram), [ElevenLabs](https://docs.pipecat.ai/server/services/tts/elevenlabs), [Fish](https://docs.pipecat.ai/server/services/tts/fish), [Google](https://docs.pipecat.ai/server/services/tts/google), [Gradium](https://docs.pipecat.ai/server/services/tts/gradium), [Groq](https://docs.pipecat.ai/server/services/tts/groq), [Hathora](https://docs.pipecat.ai/server/services/tts/hathora), [Hume](https://docs.pipecat.ai/server/services/tts/hume), [Inworld](https://docs.pipecat.ai/server/services/tts/inworld), [LMNT](https://docs.pipecat.ai/server/services/tts/lmnt), [MiniMax](https://docs.pipecat.ai/server/services/tts/minimax), [Neuphonic](https://docs.pipecat.ai/server/services/tts/neuphonic), [NVIDIA Riva](https://docs.pipecat.ai/server/services/tts/riva), [OpenAI](https://docs.pipecat.ai/server/services/tts/openai), [Piper](https://docs.pipecat.ai/server/services/tts/piper), [PlayHT](https://docs.pipecat.ai/server/services/tts/playht), [Rime](https://docs.pipecat.ai/server/services/tts/rime), [Sarvam](https://docs.pipecat.ai/server/services/tts/sarvam), [Speechmatics](https://docs.pipecat.ai/server/services/tts/speechmatics), [XTTS](https://docs.pipecat.ai/server/services/tts/xtts) |
7979
| Speech-to-Speech | [AWS Nova Sonic](https://docs.pipecat.ai/server/services/s2s/aws), [Gemini Multimodal Live](https://docs.pipecat.ai/server/services/s2s/gemini), [Grok Voice Agent](https://docs.pipecat.ai/server/services/s2s/grok), [OpenAI Realtime](https://docs.pipecat.ai/server/services/s2s/openai), [Ultravox](https://docs.pipecat.ai/server/services/s2s/ultravox), |
8080
| Transport | [Daily (WebRTC)](https://docs.pipecat.ai/server/services/transport/daily), [FastAPI Websocket](https://docs.pipecat.ai/server/services/transport/fastapi-websocket), [SmallWebRTCTransport](https://docs.pipecat.ai/server/services/transport/small-webrtc), [WebSocket Server](https://docs.pipecat.ai/server/services/transport/websocket-server), Local |
8181
| Serializers | [Exotel](https://docs.pipecat.ai/server/utilities/serializers/exotel), [Plivo](https://docs.pipecat.ai/server/utilities/serializers/plivo), [Twilio](https://docs.pipecat.ai/server/utilities/serializers/twilio), [Telnyx](https://docs.pipecat.ai/server/utilities/serializers/telnyx), [Vonage](https://docs.pipecat.ai/server/utilities/serializers/vonage) |

‎changelog/3169.added.md‎

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1 @@
1+
- Added Hathora service to support Hathora-hosted TTS and STT models (only non-streaming)

‎changelog/3349.added.md‎

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1 @@
1+
- Added `CambTTSService`, using Camb.ai's TTS integration with MARS models (mars-flash, mars-pro, mars-instruct) for high-quality text-to-speech synthesis.

‎changelog/3446.fixed.md‎

Lines changed: 8 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,8 @@
1+
- Fixed an issue where the "bot-llm-text" RTVI event would not fire for realtime (speech-to-speech) services:
2+
3+
- `AWSNovaSonicLLMService`
4+
- `GeminiLiveLLMService`
5+
- `OpenAIRealtimeLLMService`
6+
- `GrokRealtimeLLMService`
7+
8+
The issue was that these services weren't pushing `LLMTextFrame`s. Now they do.

‎changelog/3454.fixed.md‎

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1 @@
1+
- Fixed an issue where `on_user_turn_stop_timeout` could fire while a user is talking when using `ExternalUserTurnStrategies`.

‎changelog/3455.fixed.md‎

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1 @@
1+
- Fixed an issue where user turn start strategies were not being reset after a user turn started, causing incorrect strategy behavior.

‎changelog/3461.added.md‎

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1 @@
1+
- Added the `additional_headers` param to `WebsocketClientParams`, allowing `WebsocketClientTransport` to send custom headers on connect, for cases such as authentication.

‎changelog/3462.fixed.md‎

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1 @@
1+
- Fixed `MinWordsUserTurnStartStrategy` to not aggregate transcriptions, preventing incorrect turn starts when words are spoken with pauses between them.

‎changelog/3479.deprecated.md‎

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1 @@
1+
- For consistency with other package names, we just deprecated `pipecat.turns.mute` (introduced in Pipecat 0.0.99) in favor of `pipecat.turns.user_mute`.

0 commit comments

Comments
 (0)