Commit Graph

  • 039d144c79 examples(phone-bot): updated example to use Gemini (#1233) Dominic Stewart 2025-02-19 22:03:37 -08:00
  • d0f67fc189 BaseInputTransport: remove VAD logging Aleix Conchillo Flaqué 2025-02-19 21:43:29 -08:00
  • 6e3f96aa83 fish: automatically send TTSStoppedFrame after timeout Aleix Conchillo Flaqué 2025-02-19 21:39:36 -08:00
  • 293677588d tts: make push_stop_frames default to 2.0s Aleix Conchillo Flaqué 2025-02-19 21:39:00 -08:00
  • 50e9ef11e5 Update example hush/recordingIssueJan24 James Hush 2025-02-20 13:04:34 +08:00
  • 2cd8ff3848 Recording issue James Hush 2025-01-24 14:10:32 +08:00
  • 621813571a This works Dominic 2025-02-19 20:24:27 -08:00
  • 77e777b1ce Merge pull request #1249 from pipecat-ai/invoking_call_start_function Filipi da Silva Fuchter 2025-02-19 18:09:00 -03:00
  • 7e7926059c Fixed an issue that start_callback was not invoked for some LLM services. Filipi Fuchter 2025-02-19 18:04:20 -03:00
  • c948754eff Merge pull request #1248 from pipecat-ai/aleix/daily-transport-room-url Aleix Conchillo Flaqué 2025-02-19 09:46:46 -08:00
  • 83f1a8830d daily: add room_url property Aleix Conchillo Flaqué 2025-02-19 09:29:53 -08:00
  • 80f8e05fcf docs: fix transcripts in translation chatbot example (#1199) James Hush 2025-02-19 16:07:22 +08:00
  • afd1a1e80b Merge pull request #1245 from pipecat-ai/aleix/stt-mute-filter-trace-logging Aleix Conchillo Flaqué 2025-02-18 21:21:55 -08:00
  • ceefea8d63 Changed example to use gemini 2.0 flash lite Dominic 2025-02-18 19:08:22 -08:00
  • 1974474480 Updated the readme Dominic 2025-02-18 18:16:27 -08:00
  • 160d054aa5 Updated the readme Dominic 2025-02-18 18:10:34 -08:00
  • 4718f68717 Based on feedback, made the gemini file something that can be called separately Dominic 2025-02-18 18:04:29 -08:00
  • 84ac88cad7 STTMuteFilter: change suppressed logging to trace Aleix Conchillo Flaqué 2025-02-18 18:03:37 -08:00
  • 211163e5c7 Merge pull request #1241 from pipecat-ai/aleix/deepgram-nova-3 Aleix Conchillo Flaqué 2025-02-18 17:53:04 -08:00
  • 1b0bcebef6 deepgram: use the new nova-3 model as default Aleix Conchillo Flaqué 2025-02-18 09:56:09 -08:00
  • 89736b03c4 Merge pull request #1243 from pipecat-ai/aleix/add-deepgram-addons Aleix Conchillo Flaqué 2025-02-18 17:47:48 -08:00
  • 4edda718ed deepgram: add ability to provide custom addons Aleix Conchillo Flaqué 2025-02-18 13:02:11 -08:00
  • 22a62edc9e Merge pull request #1242 from pipecat-ai/aleix/utils-network-exponential Aleix Conchillo Flaqué 2025-02-18 17:44:21 -08:00
  • 50b6cc8135 network: added exponential_backoff_time() function Aleix Conchillo Flaqué 2025-02-18 10:09:49 -08:00
  • 45cf36925a Merge pull request #1240 from pipecat-ai/aleix/handle-deepgram-on-error Aleix Conchillo Flaqué 2025-02-18 17:41:29 -08:00
  • 83a71e1fec Merge pull request #1112 from pipecat-ai/bot-ready-signalling-rn Filipi da Silva Fuchter 2025-02-18 15:17:38 -03:00
  • e809c8680e Upgrading to use the latest node stable version Filipi Fuchter 2025-02-18 15:12:44 -03:00
  • c926063d74 deepgram: handle error event and reconnect Aleix Conchillo Flaqué 2025-02-18 09:39:13 -08:00
  • 0334550356 Merge pull request #1238 from pipecat-ai/aleix/stt-mute-filter-ignore-input-audio-frames Aleix Conchillo Flaqué 2025-02-18 09:48:13 -08:00
  • 90b9dce710 STTMuteFilter: ignore audio frames so no transcriptions are generated Aleix Conchillo Flaqué 2025-02-17 18:59:13 -08:00
  • f039ece2c0 feat: nova-3 example hush/nova3Example James Hush 2025-02-18 11:24:02 +08:00
  • 3a781c786c Fixed typo Dominic 2025-02-17 10:22:06 -08:00
  • a066e2bcfd Updated example to use Gemini Dominic 2025-02-17 10:17:59 -08:00
  • a5cdd5f1b8 Add Cartesia API key to dot-env.template Carl Kho 2025-02-14 21:29:37 -08:00
  • 5f937b8479 Update test requirements to include Cartesia version 1.3.1 Carl Kho 2025-02-14 21:14:32 -08:00
  • b45f7fee6f Merge pull request #1225 from pipecat-ai/aleix/prepare-0.0.57 v0.0.57 mb/add-office-ambience Aleix Conchillo Flaqué 2025-02-14 18:50:08 -08:00
  • 01c06c5cac update CHANGELOG for 0.0.57 Aleix Conchillo Flaqué 2025-02-14 14:12:02 -08:00
  • 329e89c1d9 TTSService: push BotStoppedSpeakingFrame Aleix Conchillo Flaqué 2025-02-14 17:17:47 -08:00
  • 883410d8ac FrameProcessor: no need to create an input event every time Aleix Conchillo Flaqué 2025-02-14 16:42:00 -08:00
  • 1f5b790dd0 TTSService: reset processing text during interruptions Aleix Conchillo Flaqué 2025-02-14 16:41:10 -08:00
  • a107b1cb4b examples(06a): use CartesiaTTSService Aleix Conchillo Flaqué 2025-02-14 15:57:18 -08:00
  • 63950912f0 LLMAssistantContextAggregator: add missing variable initialization Aleix Conchillo Flaqué 2025-02-14 15:55:22 -08:00
  • 2ce9402571 LLMAssistantResponseAggregator: initialize messages Aleix Conchillo Flaqué 2025-02-14 15:51:03 -08:00
  • f6912c0f9a utils: don't consider colon an end of sentence Aleix Conchillo Flaqué 2025-02-14 15:44:13 -08:00
  • 633a4d4c58 FalImageGenService: load image async to not block the event loop Aleix Conchillo Flaqué 2025-02-14 15:42:05 -08:00
  • 67da745bb3 tts: make frame pausing/resuming optional Aleix Conchillo Flaqué 2025-02-14 14:45:35 -08:00
  • 5126d4de92 tts: handle incoming frames pausing/resuming from base TTSService class Aleix Conchillo Flaqué 2025-02-14 14:34:38 -08:00
  • 426d7ac213 transports: some local audio and tk updates Aleix Conchillo Flaqué 2025-02-14 13:11:35 -08:00
  • 9115692c72 Merge pull request #1227 from pipecat-ai/mb/fix-25-error Mark Backman 2025-02-14 21:01:05 -05:00
  • c26fe3f277 fix: ensure proper Google message format conversion in transcription filter Mark Backman 2025-02-14 20:28:26 -05:00
  • 47b059d387 Merge pull request #1226 from pipecat-ai/mb/add-transcript-processor-tests Mark Backman 2025-02-14 19:50:38 -05:00
  • a49d81e519 tests: add tests for TranscriptProcessor Mark Backman 2025-02-14 17:06:04 -05:00
  • b3a575c7c7 Merge pull request #1212 from Vaibhav159/vl_fix_incorrect_has_regular_messages_check Aleix Conchillo Flaqué 2025-02-14 13:16:37 -08:00
  • 790d0c1256 Merge pull request #1224 from M1ngXU/patch-1 Aleix Conchillo Flaqué 2025-02-14 13:13:00 -08:00
  • ee7e0dc3f7 Merge pull request #1223 from pipecat-ai/aleix/audio-context-tts-service Aleix Conchillo Flaqué 2025-02-14 12:12:42 -08:00
  • f53ee79ddb RimeTTSService: use AudioContextWordTTSService Aleix Conchillo Flaqué 2025-02-14 11:39:05 -08:00
  • aeadb40c3f CartesiaTTSService: use AudioContextWordTTSService Aleix Conchillo Flaqué 2025-02-14 11:18:35 -08:00
  • cacb07f4c2 introduce AudioContextWordTTSService Aleix Conchillo Flaqué 2025-02-14 11:18:24 -08:00
  • 0b91d821fb Update openai.py M1ngXU 2025-02-14 20:27:08 +01:00
  • af66a43056 Merge pull request #1222 from pipecat-ai/aleix/websocket-service-handle-clean-disconnection Aleix Conchillo Flaqué 2025-02-14 10:33:54 -08:00
  • e006dcf172 WebsocketService: handle clean server disconnection Aleix Conchillo Flaqué 2025-02-14 09:54:03 -08:00
  • 8588f8b0d8 Merge pull request #1220 from pipecat-ai/instant_voice_demo_example Filipi da Silva Fuchter 2025-02-14 14:24:13 -03:00
  • bff54547b0 Instant voice example. Filipi Fuchter 2025-02-14 14:19:17 -03:00
  • b2754bf208 Merge pull request #1219 from pipecat-ai/mb/markdown-text-filter-tests Mark Backman 2025-02-13 21:10:52 -05:00
  • 9a4942b0d0 Merge pull request #1218 from pipecat-ai/mb/user-idle-tests Mark Backman 2025-02-13 18:53:22 -05:00
  • ed6201910b Add MarkdownTextFilter tests Mark Backman 2025-02-13 16:12:24 -05:00
  • ac5ebc587e Add tests for UserIdleProcessor Mark Backman 2025-02-13 15:32:27 -05:00
  • dff4c54e57 Merge pull request #1209 from pipecat-ai/aleix/reimplement-llm-response-aggregators Aleix Conchillo Flaqué 2025-02-13 15:30:40 -08:00
  • c744409651 SegmentedSTTService: fix process_audio_frame() arguments Aleix Conchillo Flaqué 2025-02-13 14:49:00 -08:00
  • 7578fbeaef update google requirements Aleix Conchillo Flaqué 2025-02-13 14:07:30 -08:00
  • 5909dff423 LLMContextResponseAggregator: add VAD emulation support Aleix Conchillo Flaqué 2025-02-13 13:59:43 -08:00
  • a6502df72c services: forgot to pass context instead of user aggregator Aleix Conchillo Flaqué 2025-02-13 13:50:33 -08:00
  • e0d24d7fc0 update CHANGELOG Aleix Conchillo Flaqué 2025-02-13 13:21:32 -08:00
  • 99779046a8 services: use push_context_frame() Aleix Conchillo Flaqué 2025-02-13 13:19:46 -08:00
  • 67cdc0063a BaseTransportOutput: allow pushing frames upstream Aleix Conchillo Flaqué 2025-02-13 13:17:57 -08:00
  • b28f752afa tests: add anthropic and google aggregator tests Aleix Conchillo Flaqué 2025-02-13 13:08:34 -08:00
  • 463078e375 initialize assistant aggregators with context and push upstream instead Aleix Conchillo Flaqué 2025-02-13 11:48:04 -08:00
  • 84510fd521 LLMUserContextAggregator: add space between transcriptions Aleix Conchillo Flaqué 2025-02-13 07:24:05 -08:00
  • 9f6a1c093a LLMUserContextAggregator: reset user speaking time after bot interruption Aleix Conchillo Flaqué 2025-02-12 23:54:59 -08:00
  • b602e78625 tests: add OpenAI context aggregator tests Aleix Conchillo Flaqué 2025-02-12 23:29:45 -08:00
  • 7c815121ea LLMContextResponseAggregator: add missing reset() implementation Aleix Conchillo Flaqué 2025-02-12 23:29:19 -08:00
  • 16a107948b services: missing kwargs in anthropic/openai user context aggregator Aleix Conchillo Flaqué 2025-02-12 23:28:36 -08:00
  • 839aa7d935 llm_response: add some initial docstrings to LLM aggregators Aleix Conchillo Flaqué 2025-02-12 19:14:24 -08:00
  • 4cbcfe2b0b LLMUserContextAggregator: interrupt the bot if VAD happened a while back Aleix Conchillo Flaqué 2025-02-12 18:53:51 -08:00
  • 91a628d1ba UserResponseAggregator: implement on top of LLMUserResponseAggregator Aleix Conchillo Flaqué 2025-02-12 13:53:47 -08:00
  • 50288eeaaa tests: add LLM response aggregators tests Aleix Conchillo Flaqué 2025-02-11 22:16:20 -08:00
  • e1f2bbceb3 reimplement LLM response aggregators Aleix Conchillo Flaqué 2025-02-11 22:16:10 -08:00
  • 8bdd7ed0ed tests: implement langchain tests with run_test() Aleix Conchillo Flaqué 2025-02-11 22:14:27 -08:00
  • 1b7dfe8126 tests: add a new SleepFrame Aleix Conchillo Flaqué 2025-02-11 22:13:07 -08:00
  • d1ee851a65 tests: rename some variables to make things clearer Aleix Conchillo Flaqué 2025-02-11 22:12:48 -08:00
  • 0358673b46 Merge pull request #1215 from pipecat-ai/instant_voice_demo Filipi da Silva Fuchter 2025-02-13 18:14:15 -03:00
  • 16fe1b10e9 - Added support for the RTVIProcessor to handle buffered audio in base64 format, converting it into InputAudioRawFrame for transport. - Added support for the RTVIProcessor to trigger start_audio_in_streaming only after the client-ready message. Filipi Fuchter 2025-02-13 18:08:55 -03:00
  • f001819df8 - Added a new audio_in_stream_on_start field to TransportParams. - Added a new method start_audio_in_streaming in the BaseInputTransport. - Updated DailyTransport to respect the audio_in_stream_on_start field, ensuring it only starts receiving the audio input if it is enabled. Filipi Fuchter 2025-02-13 18:08:36 -03:00
  • dceec60186 Updated FastAPIWebsocketOutputTransport to send TransportMessageFrame and TransportMessageUrgentFrame to the serializer. Filipi Fuchter 2025-02-13 18:07:33 -03:00
  • b96979a4ed Update WebsocketServer to not wrap the message inside a text frame. Filipi Fuchter 2025-02-13 18:07:04 -03:00
  • 745c40def4 Merge pull request #1214 from pipecat-ai/mb/stt-mute-tests Mark Backman 2025-02-13 09:50:43 -05:00
  • 42ab62716d Merge pull request #1198 from pipecat-ai/mb/more-whisper-params Mark Backman 2025-02-13 09:16:38 -05:00
  • 16ba2010aa Refactor process_frame to be more consistent Mark Backman 2025-02-13 09:15:29 -05:00
  • ec0ca46617 Fix temperature docstrings to reference optional Mark Backman 2025-02-13 09:04:20 -05:00
  • 6ff1f526ff Merge pull request #1216 from pipecat-ai/mb/google-cloud-speech Mark Backman 2025-02-13 07:04:34 -05:00