Commit Graph

  • aa0b49d69f Code review fixes Mark Backman 2026-03-24 09:19:43 -04:00
  • 8c6f4a8d7b Add Novita AI LLM service provider Alex-wuhu 2026-03-24 19:53:18 +08:00
  • bbaa5971c4 Merge pull request #3981 from dhruvladia-sarvam/feat/sarvam-llm-integration Mark Backman 2026-03-24 09:00:01 -04:00
  • cdd8c3e5bb Fix examples Mark Backman 2026-03-24 08:53:56 -04:00
  • 1c8a8f51d4 Code review fixes Mark Backman 2026-03-24 08:46:03 -04:00
  • 349b8645f3 Merge branch 'main' into feat/sarvam-llm-integration dhruvladia-sarvam 2026-03-24 16:34:12 +05:30
  • 696196e30c alignment with pr 4081 dhruvladia-sarvam 2026-03-24 16:29:58 +05:30
  • dacffccd3a fixed runtime issue. Garegin Harutyunyan 2026-03-24 12:56:19 +04:00
  • f21b262969 feat(assemblyai): add domain parameter for Medical Mode Martin Schweiger 2026-03-24 13:09:42 +08:00
  • 7414b30308 Merge pull request #4116 from pipecat-ai/changelog-0.0.107 v0.0.107 Aleix Conchillo Flaqué 2026-03-23 20:13:49 -07:00
  • 3268cb93d5 Update changelog for version 0.0.107 aconchillo 2026-03-24 03:07:36 +00:00
  • 9211379720 update uv.lock Aleix Conchillo Flaque 2026-03-23 20:06:28 -07:00
  • 42cab7eea0 Add changelog entry for #4115 Mark Backman 2026-03-23 18:01:04 -04:00
  • 483b643b07 Warn when VAD stop_secs misconfiguration may degrade turn detection Mark Backman 2026-03-23 17:57:51 -04:00
  • 12dc429761 Merge pull request #4104 from pipecat-ai/filipi/audio_issue Filipi da Silva Fuchter 2026-03-23 17:17:37 -04:00
  • 066b206b3d Renaming insert_silence to auto_silence filipi87 2026-03-23 18:12:26 -03:00
  • ddd1b71b56 Renaming audio_out_insert_silence to audio_out_auto_silence filipi87 2026-03-23 17:57:42 -03:00
  • 8612c9f50a Updating to use daily-python 0.27.0 filipi87 2026-03-23 17:52:41 -03:00
  • d314e2831a Simplify 26 name, update evals Mark Backman 2026-03-23 15:46:13 -04:00
  • fd0bfe141f Merge pull request #4109 from pipecat-ai/pk/tiny-fix Mark Backman 2026-03-23 15:17:19 -04:00
  • 3042929989 Fixing changelog description. filipi87 2026-03-23 15:57:25 -03:00
  • 0f6cc231cf removing error wraps and model validation check dhruvladia-sarvam 2026-03-24 00:06:15 +05:30
  • 844555c520 removed old Gemini Live example Chad Bailey 2026-03-23 18:31:36 +00:00
  • 3428a4c6ad fixes post PR 4081 dhruvladia-sarvam 2026-03-23 23:45:27 +05:30
  • f283cc5bc6 Merge pull request #4091 from pipecat-ai/mb/gradium-multiplexing-setup Mark Backman 2026-03-23 12:00:53 -04:00
  • 70552d7697 Add changelog entry for #4091 Mark Backman 2026-03-20 11:35:25 -04:00
  • 84c2a24c9f feat: send per-context setup messages in Gradium TTS multiplexing Mark Backman 2026-03-20 11:33:18 -04:00
  • f8c7414ea7 format fix. Garegin Harutyunyan 2026-03-23 18:57:48 +04:00
  • f1f51de962 Merge branch 'main' into krisp-viva-vad-support Garegin Harutyunyan 2026-03-23 18:35:58 +04:00
  • e93b0ace06 Remove an unnecessary check in SyncParallelPipeline Paul Kompfner 2026-03-23 10:00:32 -04:00
  • c32240e14b Fixed review comments. Garegin Harutyunyan 2026-03-23 17:44:48 +04:00
  • 3bacc3beb6 Add Sarvam LLM to README list mb/sarvam-llm-settings-refactor Mark Backman 2026-03-23 09:16:12 -04:00
  • c6c14d5887 Remove error-wrapping overrides and align class docstring Mark Backman 2026-03-23 09:12:31 -04:00
  • eea7fa381e Remove unreachable tool-model validation check Mark Backman 2026-03-19 09:14:50 -04:00
  • 696123f2c5 Update 07z foundational examples to use SarvamLLMService Mark Backman 2026-03-19 09:03:38 -04:00
  • 99b478b897 Use Settings pattern and access self._settings directly for Sarvam-specific params Mark Backman 2026-03-19 09:00:14 -04:00
  • edf4ba45a5 wrapper fixes dhruvladia-sarvam 2026-03-17 02:47:47 +05:30
  • 9bbc28bc9a fix llm wrapper redundancy and restore run_inference parity dhruvladia-sarvam 2026-03-15 22:24:06 +05:30
  • 04f8c8a87e Initial dhruvladia-sarvam 2026-03-11 02:27:57 +05:30
  • e6602f9244 Disabling auto_silence for tavus video service. filipi87 2026-03-22 18:28:57 -03:00
  • 9a30b18f21 Configuring Daily CustomAudioSource to automatically inject silence or not. filipi87 2026-03-22 17:29:01 -03:00
  • 936a39f4a1 Updating tavus examples to not send silence. filipi87 2026-03-22 14:41:23 -03:00
  • 3b1cb30926 Adding changelog entry. filipi87 2026-03-22 13:26:00 -03:00
  • ce36487143 Allow defining whether to insert silence in the output transport. filipi87 2026-03-22 13:09:09 -03:00
  • ec3bd8c5b1 Merge pull request #4097 from pipecat-ai/mb/update-minimax-docs-link Mark Backman 2026-03-21 07:08:40 -04:00
  • 622ebd5d74 Update MiniMaxHttpTTSService platform docs link Mark Backman 2026-03-21 07:02:06 -04:00
  • 4cb699b64c Align Together STT/TTS services with Pipecat patterns add_together_stt_tts Mark Backman 2026-03-20 22:22:27 -04:00
  • 4262410812 chore: rename changelog fragment to PR #4093 Pablo Ois Lagarde 2026-03-20 16:46:35 -03:00
  • 086aff27a8 fix: always include parameters field in Genesys AudioHook messages Pablo Ois Lagarde 2026-03-20 16:37:53 -03:00
  • e4a82ffcac refactor: align tracing attributes with OpenTelemetry GenAI conventions Mark Backman 2026-03-20 13:36:20 -04:00
  • 20a3ada916 refactor: rename tracing span attribute "system" to "system_instructions" Mark Backman 2026-03-20 13:20:03 -04:00
  • 991fbb82da fix: read system_instruction from _settings instead of removed attribute Mark Backman 2026-03-20 13:12:40 -04:00
  • 112d1bd375 Improve system message extraction in traced_llm Kinshuk Bairagi 2026-01-14 21:46:58 +05:30
  • 7f9f151b7c enable_dialout should not depend on sip_caller_phone being set (#4087) Varun Singh 2026-03-20 10:01:31 -07:00
  • 9edbe60c8c Add changelog entry for #4090 Mark Backman 2026-03-20 10:46:36 -04:00
  • 7de260abe7 fix: route TTS audio through audio context queue in Fish, LMNT, Neuphonic, Rime NonJson Mark Backman 2026-03-20 10:41:43 -04:00
  • 073318be91 Add community integrations to README Mark Backman 2026-03-20 10:09:58 -04:00
  • 0778116a55 Changelog entry for the DeepgramSageMakerTTSService improvements. filipi87 2026-03-19 11:46:49 -03:00
  • efba4f2c7a Routing the audio through the audio context queue. filipi87 2026-03-19 11:40:43 -03:00
  • 0afd8bf341 Improvements to DeepgramSageMakerTTSService. filipi87 2026-03-19 11:32:56 -03:00
  • 7e06b99029 Adding changelog entry for the Sarvam fixes. filipi87 2026-03-19 11:17:39 -03:00
  • bd834083da Improvements to SarvamTTSService. filipi87 2026-03-19 11:13:17 -03:00
  • aec8d13eec Remove 05a example, which was broken and isn't currently a priority to fix Paul Kompfner 2026-03-19 15:52:48 -04:00
  • 3b5a8acfe2 fix: typo "conversatione" → "conversation" in 20- examples Paul Kompfner 2026-03-19 15:38:38 -04:00
  • 6ee49333f3 docs: note input_audio coming soon, no conversion needed Paul Kompfner 2026-03-19 15:36:23 -04:00
  • f33f2d7640 refactor: remove model init param from OpenAIResponsesLLMService Paul Kompfner 2026-03-19 14:37:46 -04:00
  • eb3affd45b docs: port _closing comments from BaseOpenAILLMService Paul Kompfner 2026-03-19 14:30:34 -04:00
  • 0ae6a8b63a feat: include cached_tokens and reasoning_tokens in usage metrics Paul Kompfner 2026-03-19 14:23:39 -04:00
  • 35903905f8 refactor: use direct attribute access for typed stream events Paul Kompfner 2026-03-19 14:19:10 -04:00
  • f680f3c1fa fix: prefer _full_model_name over _settings.model in tracing Paul Kompfner 2026-03-19 13:55:26 -04:00
  • 3ddb7b4aaf fix: remove redundant instructions override in run_inference Paul Kompfner 2026-03-19 13:34:41 -04:00
  • 6b8bca3d93 feat: add 12- and 14d- image/video examples for OpenAI Responses Paul Kompfner 2026-03-18 15:39:06 -04:00
  • 0bb0874275 feat: add service_tier support to OpenAIResponsesLLMService Paul Kompfner 2026-03-18 15:29:04 -04:00
  • e1f31ff878 feat: add 55zi update-settings example for OpenAI Responses Paul Kompfner 2026-03-18 15:17:16 -04:00
  • 2f2c0909f1 feat: add 20a persistent context example for OpenAI Responses Paul Kompfner 2026-03-18 15:14:28 -04:00
  • ea89819ece chore: update previous_response_id comment Paul Kompfner 2026-03-18 15:06:54 -04:00
  • c66a5a8ede feat: set store=False and add run_inference tests Paul Kompfner 2026-03-18 14:47:12 -04:00
  • cd2886a4a8 chore: add note about previous_response_id and empty input handling Paul Kompfner 2026-03-18 14:26:51 -04:00
  • 312837a1d4 test: add run_inference tests for OpenAIResponsesLLMService Paul Kompfner 2026-03-18 14:17:21 -04:00
  • 4d4e56cfef test: add run_inference tests for OpenAIResponsesLLMService Paul Kompfner 2026-03-18 14:09:17 -04:00
  • 05e1d9f514 docs: add changelog for OpenAI Responses API service Paul Kompfner 2026-03-18 11:46:49 -04:00
  • 4d548117fa feat: add OpenAI Responses API LLM service Paul Kompfner 2026-03-18 11:45:23 -04:00
  • b5c2d41ba3 Remove changelog fragment that no longer applies after a rebase Paul Kompfner 2026-03-19 09:57:26 -04:00
  • dba2fc5451 Clarify SyncParallelPipeline docstrings Paul Kompfner 2026-03-18 16:39:20 -04:00
  • 0a4acfa294 Add frame_order parameter to SyncParallelPipeline Paul Kompfner 2026-03-16 09:59:13 -04:00
  • ffdf629535 Add changelog entry for Whisker debugger fix Paul Kompfner 2026-03-13 22:20:53 -04:00
  • a6b94c7424 Add changelog entries for PR #4029 Paul Kompfner 2026-03-13 22:15:32 -04:00
  • d2341e0199 Add ImageBeforeAudioReorderer to sync-speech-and-image example Paul Kompfner 2026-03-13 22:09:44 -04:00
  • 4b66dd444b Revert a couple of logs that were changed from trace to debug just for debugging Paul Kompfner 2026-03-13 21:04:16 -04:00
  • 7b859423ab Use TextAggregationMode.TOKEN in the 05-sync-speech-and-image example since the SentenceAggregator already provides complete sentences. Paul Kompfner 2026-03-13 18:43:54 -04:00
  • b68495ce0a Add sync_with_audio support for OutputImageRawFrame Paul Kompfner 2026-03-13 15:15:45 -04:00
  • f39472b150 Fix SyncParallelPipeline race condition with concurrent SystemFrame processing Paul Kompfner 2026-03-13 14:17:35 -04:00
  • a8ea176ea3 Minor comment typo fix Paul Kompfner 2026-03-13 13:40:26 -04:00
  • 12cb9599ad Fix bug resulting in SyncParallelPipeline breaking the Whisker debugger Paul Kompfner 2026-03-13 12:29:32 -04:00
  • 167f008e47 Mentioning the frame order fix in the changelog. filipi87 2026-03-19 10:26:58 -03:00
  • fe8cb2f4e0 Always appending TTSTextFrame to the audio context. filipi87 2026-03-19 10:12:01 -03:00
  • cdf44f7a3f Fixing the frame ordering of the AggregatedTextFrame. filipi87 2026-03-19 10:07:25 -03:00
  • d32a8a9ee2 Fixing TTS frame order. filipi87 2026-03-19 09:43:40 -03:00
  • ed160fd2e0 fix(livekit): suppress InvalidState log spam from audio mixer during interruptions joachimchauvet 2026-03-18 16:04:42 +02:00
  • 84eddb64d5 Update changelog for version 0.0.106 aconchillo 2026-03-19 04:48:16 +00:00