Commit Graph

2072 Commits

Author SHA1 Message Date
Adithya Suresh
b2b01861b2 Remove model restriction 2025-05-07 09:26:26 -07:00
Adithya Suresh
f014f718eb Restructured STT and enabled prosody tags for generative Polly 2025-05-07 09:26:26 -07:00
Adithya Suresh
05ae8d3ffa Removed OpenAI based context formatting 2025-05-07 09:26:26 -07:00
Adithya Suresh
88c9e08bd8 Updated tools parsing logic 2025-05-07 09:26:26 -07:00
Adithya Suresh
844f61dfea Initial implementation 2025-05-07 09:26:26 -07:00
Tico Ballagas
2b18f60261 Initial implementation of AWS Transcribe TTS 2025-05-07 09:19:49 -07:00
Dan Berg
5e39c0cfeb DailyTransport: added on_active_speaker_changed event handler 2025-05-07 15:22:30 +02:00
Mark Backman
a1d46cb26b Removing CanonicalMetricsService 2025-05-06 21:23:23 -04:00
Aleix Conchillo Flaqué
0d30b000af BaseObserver: add FramePushed class and deprecated multiple arguments 2025-05-06 15:26:23 -07:00
Mark Backman
e7c0e742d2 Merge pull request #1752 from pipecat-ai/mb/deepgram-tts-aura-2
Update Deepgram TTS default voice to Aura 2 voice
2025-05-06 16:26:26 -04:00
Mark Backman
2aff2dcca3 Merge pull request #1751 from pipecat-ai/mb/11labs-enable_ssml_parsing
Add enable_ssml_parsing and enable_logging to ElevenLabsTTSService
2025-05-06 16:25:20 -04:00
Mark Backman
288f8865c8 Add enable_logging to ElevenLabsTTSService 2025-05-06 12:13:26 -04:00
Mark Backman
8691870bcb Update Deepgram TTS default voice to Aura 2 voice 2025-05-06 11:29:32 -04:00
Mark Backman
e06146c237 Add enable_ssml_parsing to ElevenLabsTTSService 2025-05-06 11:06:57 -04:00
Aleix Conchillo Flaqué
c68e990cda Merge pull request #1748 from pipecat-ai/aleix/task-manager-dictionary
task manager dictionary and cleanup PipelineTask
2025-05-06 07:57:53 -07:00
Aleix Conchillo Flaqué
4583905313 PipelineTask: cleanup if task is cancelled from outside Pipecat 2025-05-05 21:33:21 -07:00
Aleix Conchillo Flaqué
9cc498b1fa TaskManager: use a dictionary instead of a set to store tasks 2025-05-05 21:27:49 -07:00
Mark Backman
b3c5dc4045 Merge pull request #1443 from adithyaxx/anthropic-client-bug-fixes
Handle missing token counts in AsyncAnthropicBedrock client properly
2025-05-05 21:13:11 -04:00
Aleix Conchillo Flaqué
855d567b1e only send data to transports after they are really ready 2025-05-05 14:06:58 -07:00
Aleix Conchillo Flaqué
e15fa8777a Merge pull request #1737 from CerebriumAI/kyle/fix-ultravox-spacing
[Fix] Ultravox frame spacing issue
2025-05-05 09:34:49 -07:00
Aleix Conchillo Flaqué
044e2d3e73 DailyTransport: remove custom tracks before leaving 2025-05-05 08:35:35 -07:00
Kyle Gani
be112ec63f Merge branch 'kyle/fix-ultravox-performance' of github.com:CerebriumAI/pipecat into kyle/fix-ultravox-performance 2025-05-05 17:13:26 +02:00
Kyle Gani
d2f56c4e8f Fix: Spacing issue 2025-05-05 17:13:21 +02:00
Kwindla Hultman Kramer
b25f3b2ed2 support for rime arcana model 2025-05-05 10:50:46 -04:00
Aleix Conchillo Flaqué
54971a0735 update to daily-python 0.18.1 2025-05-02 17:47:44 -07:00
Mark Backman
4513e81e13 Merge pull request #1723 from pipecat-ai/mb/base-output-bot-speaking-log
Only display the destination in the bot started/stopped speaking log …
2025-05-02 17:32:47 -04:00
Mark Backman
872204b795 Only display the destination in the bot started/stopped speaking log when there is a desintation 2025-05-02 17:29:28 -04:00
Aleix Conchillo Flaqué
7152faafb2 BaseOutputTransport: always initialize audio task
We also use the audio task to also send synchronized images with audio.
2025-05-02 14:23:15 -07:00
Mark Backman
e6aadaccd8 Merge pull request #1721 from pipecat-ai/mb/simli-silent-frames
Fix: SimliVideoService was continuously emitting audio, preventing Bo…
2025-05-02 16:44:39 -04:00
vipyne
b2754117c8 Riva: refactor function_id and model_name 2025-05-02 15:33:10 -05:00
vipyne
6c428c303b update magpie voice 2025-05-02 15:33:10 -05:00
Mark Backman
e7d889a143 Update RivaSTTService to use by default 2025-05-02 15:33:10 -05:00
Mark Backman
725ab5ec21 Small fixes: No default api_key of None, ParakeetSTTService uses RivaSTTService.InputParams 2025-05-02 15:33:10 -05:00
Mark Backman
daf9d47e58 Update RivaSegmentedSTTService 2025-05-02 15:33:10 -05:00
vipyne
63a65627a2 Riva Service: add magpie-tts-multilingual model 2025-05-02 15:33:10 -05:00
Matt Kim
15cbd18acc [Rime] Add phonemizeBetweenBrackets and pauseBetweenBrackets to RimeTTSService (ws)
There is a fix incoming in
2025-05-02 15:33:10 -05:00
Mark Backman
eeaa9f67a1 Fix: SimliVideoService was continuously emitting audio, preventing BotStoppedSpeakingFrame from being sent 2025-05-02 16:32:42 -04:00
Mark Backman
047ef9f86c Merge pull request #1707 from rimelabs/matt/rime/url_param_serialization
[Rime] Add new params to RimeTTSService
2025-05-02 16:08:01 -04:00
Filipi da Silva Fuchter
94c4169407 Merge pull request #1717 from pipecat-ai/local_smart_turn_torch
Local smart turn torch
2025-05-02 15:53:30 -03:00
Filipi Fuchter
779f09af70 Fixing lint. 2025-05-02 14:22:38 -03:00
Filipi Fuchter
f0709e22ba Creating a local smart turn using torch. 2025-05-02 14:21:29 -03:00
Mark Backman
8250736f5e Merge pull request #1708 from pipecat-ai/mb/gemini-user-context
Push GeminiMultimodalLiveLLMService TranscriptionFrame Upstream, remo…
2025-05-02 13:10:27 -04:00
Mark Backman
83348a9f93 Merge pull request #1714 from pipecat-ai/mb/fix-gemini-text-modality
Restore TEXT modalities support to GeminiMultimodalLiveLLMService
2025-05-02 10:41:05 -04:00
Mark Backman
96d40903a9 Only send TTSStoppedFrame from Gemini when in AUDIO mode, only send one LLMFullResponseEndFrame 2025-05-02 10:18:53 -04:00
Aleix Conchillo Flaqué
2560811805 Merge pull request #1697 from pipecat-ai/aleix/daily-custom-audio-tracks
add support for multiple transport destinations
2025-05-02 06:34:09 -07:00
Mark Backman
2b8c44c008 Merge pull request #1710 from pipecat-ai/mb/openai-context-aggregation
fix: OpenAIRealtimeBetaLLMService writes two assistant messages to th…
2025-05-02 07:43:35 -04:00
Mark Backman
38e2d37674 Restore TEXT modalities support to GeminiMultimodalLiveLLMService 2025-05-02 07:36:12 -04:00
Aleix Conchillo Flaqué
750e79c1ce DailyParams: rename to camera/microphone_out_enabled 2025-05-01 19:17:14 -07:00
Aleix Conchillo Flaqué
f44e2c86ea BaseOutputTransport: compute sample_rate and audio_chunk_size in main class 2025-05-01 19:17:14 -07:00
Aleix Conchillo Flaqué
afe1f0df8c DailyTransport: make sure we can write audio frames to destination 2025-05-01 19:17:14 -07:00