wx44wx/pipecat
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
6,493 Commits 276 Branches 111 Tags
66088837cd627c49dd2fd8a4c2c50e36f5d6814c
Commit Graph

3485 Commits

Author SHA1 Message Date
Ashot
66088837cd Fixed defualt language issue in async tts 2025-12-05 16:51:05 +04:00
Ashot
e65974c870 Added new languages support for AsyncAI 2025-12-04 16:15:28 +04:00
marcus-daily
39bca074d7 Smart Turn v3.1 2025-12-04 11:32:16 +00:00
Aleix Conchillo Flaqué
b5e79f9dc5 Merge pull request #3181 from pipecat-ai/aleix/sync-to-utils-sync 
move pipecat.sync to pipecat.utils.sync
 2025-12-03 19:41:18 -08:00
Aleix Conchillo Flaqué
613b96819f Merge pull request #3180 from pipecat-ai/aleix/deepgram-tts-service-fix 
DeepgramTTSService: fix websocket header logging
 2025-12-03 19:40:43 -08:00
Mark Backman
d79dd94019 Make aggregate return an AsyncIterator, other clean up 2025-12-03 22:00:34 -05:00
Mark Backman
fa8e7458e1 Clean up 2025-12-03 22:00:04 -05:00
Mark Backman
4d66191963 fix: PatternPairAggregator to process patterns only once 2025-12-03 22:00:04 -05:00
Mark Backman
7e9d67002e SkipTagsAggregator and PatternPairAggregator now subclass SimpleTextAggregator 2025-12-03 22:00:04 -05:00
Mark Backman
ffbb6e5937 Update SimpleTextAggregator to handle character by character input, use a buffer to handle ambiguous EOS scenarios, and add a flush method to all aggregators 2025-12-03 22:00:02 -05:00
Mark Backman
535b85cf90 Add split_text_by_spaces string util 2025-12-03 21:55:30 -05:00
Aleix Conchillo Flaqué
8dc9872ed5 deprecate pipecat.sync package 2025-12-03 18:44:41 -08:00
Aleix Conchillo Flaqué
f37a53cc25 utils(sync): move sync to utils.sync 2025-12-03 18:20:12 -08:00
Aleix Conchillo Flaqué
9cce28c64c DeepgramTTSService: use websocket response headers for logging 2025-12-03 18:16:25 -08:00
Aleix Conchillo Flaqué
3ca94363ec Merge pull request #3168 from pipecat-ai/aleix/dont-override-skip-tts 
LLMTextFrame: don't override skip_tts
 2025-12-03 18:15:50 -08:00
Jason Maldonis
2df91f4b37 fixed linting 2025-12-03 08:09:16 -06:00
Jason Maldonis
7db49b9067 deepgram: added request IDs to debug logs 
Deepgram request IDs are necessary for investigating behavior at the
request level. This commit adds DEBUG logs that print Deepgram request
IDs when using Deepgram's STT or TTS.
 2025-12-03 08:09:13 -06:00
vipyne
acba544e6f pr notes for nvidia service name change 2025-12-01 22:41:17 -06:00
vipyne
5d93c64ee5 typo fixes and uv.lock update 2025-12-01 22:41:17 -06:00
vipyne
36f5c1722d deprecate riva and nim service paths in favor of nvidia 2025-12-01 22:41:17 -06:00
vipyne
05d65dfdd3 Update NVIDIA NIM and Riva services to Nvidia 
- pip install pipecat-ai[nim]
- pip install pipecat-ai[riva]

+ pip install pipecat-ai[nvidia]

and

- from pipecat.services.nim.llm import NimLLMService
+ from pipecat.services.nvidia.llm import NvidiaLLMService

- from pipecat.services.riva.stt import RivaSTTService
+ from pipecat.services.nvidia.stt import NvidiaSTTService

- from pipecat.services.riva.tts import RivaTTSService
+ from pipecat.services.nvidia.tts import NvidiaTTSService
 2025-12-01 22:41:17 -06:00
Aleix Conchillo Flaqué
a3962e3b47 LLMTextFrame: don't override skip_tts 2025-12-01 18:37:07 -08:00
Aleix Conchillo Flaqué
bff8747e38 LLMService: allow waiting for all function calls to complete 2025-12-01 18:30:25 -08:00
Mark Backman
9ccde60521 fix: flush audio in SarvamTTSService 2025-12-01 17:18:34 -05:00
Mark Backman
e72b135a4c fix: DeepgramTTSService, let the base class push TTSStoppedFrame 2025-12-01 17:15:51 -05:00
Mark Backman
89d9ca045a fix: AWSTranscribeSTTService always set to us-east-1 2025-12-01 13:02:08 -05:00
Corvin Jaedicke
6dd9ed03b1 bump version to include new STT model, noise gate deprecation warning 2025-11-28 15:14:43 +01:00
Filipi Fuchter
dedea7c420 Fixing runner ICE servers to be compatible with what is expected by the mobile SDKs. 2025-11-27 09:27:26 -03:00
Mark Backman
bedd40ae8b Fix error handling in DeepramSageMakerSTTService 2025-11-26 20:12:31 -05:00
Mark Backman
ace95b6e6d fix: AWSBedrockLLMService was always set to us-east-1 2025-11-26 19:52:04 -05:00
Aleix Conchillo Flaqué
81f862749d SimliVideoService: add enable_logging input parameter 2025-11-26 16:36:06 -08:00
Filipi Fuchter
4acc317923 Fixed an issue with DeepgramFluxSTTService where it sometimes failed to reconnect. 2025-11-26 20:23:03 -03:00
Filipi Fuchter
1330ef3ad6 Enhanced error handling across the framework. 
Co-authored-by: Mark Backman <m.backman@gmail.com>
 2025-11-26 18:34:25 -03:00
Mark Backman
6d93b8e9d8 Update DeepgramTTSService to use Deepgram's Websocket TTS API 2025-11-26 13:25:34 -05:00
Aleix Conchillo Flaqué
6cf1d0417e Merge pull request #3136 from kcui5/patch-1 
Update Fish Audio default model to s1
 2025-11-26 10:19:26 -08:00
Kyle Cui
7fa0cbf2a9 Update Fish Audio default model to s1 
Update default model from speech-1.5 to s1 for Fish Audio TTS service
 2025-11-26 01:50:38 -08:00
Thu Nguyen
42be0183af Merge branch 'main' into feat/add-cached-reasoning-tokens-metrics-to-opentel-spans 2025-11-26 12:59:43 +07:00
Mark Backman
2607699664 Merge pull request #3125 from pipecat-ai/mb/fix-sagemaker-imports 
fix: remove stt_sagemaker import from deepgram/__init__.py
 2025-11-24 21:31:31 -05:00
Mark Backman
47fa3b8556 Merge pull request #3108 from fbarril/livekit-transport-helper 
add livekit helper
 2025-11-24 20:13:13 -05:00
Mark Backman
fa0100c38b fix: remove stt_sagemaker import from deepgram/__init__.py 2025-11-24 20:04:18 -05:00
Paul Kompfner
5907b51c7d In AWSBedrockAgentCoreProcessor use self.create_task()/self.cancel_task() instead of using asyncio directly. 2025-11-24 18:53:39 -05:00
Paul Kompfner
9e4ec4f7f3 Implement AWSBedrockAgentCoreProcessor 2025-11-24 18:53:35 -05:00
fbarril
7c81f66241 Merge remote-tracking branch 'origin/main' into livekit-transport-helper 
# Conflicts:
#	CHANGELOG.md
#	uv.lock
 2025-11-24 23:29:22 +00:00
Mark Backman
782b257bbb Add DeepgramSageMakerSTTService 2025-11-24 16:41:01 -05:00
Mark Backman
ab8dcd6ede Add SageMaker BiDi client 2025-11-24 16:41:00 -05:00
Mark Backman
7bdac02837 Fix sample_rate issue in ElevenLabsRealtimeSTTService, add timestamps and logging 2025-11-24 08:06:33 -05:00
Dante Noguez
3458b74fc9 Fix 11labs realtime dynamic updates (#3117) 2025-11-22 10:02:37 -05:00
mattie ruth backman
a6202c4d1a Fixed CHANGELOG post rebase 2025-11-21 17:16:10 -05:00
mattie ruth backman
8b8b57b09c Introduced new bot-output RTVI event to provide... 
a best effort version of the bot's output

- The `RTVIObserver` now emits `bot-output` messages based off
  the new `AggregatedTextFrame`s (`bot-tts-text` and
  `bot-llm-text` are still supported and generated, but
  `bot-transcript` is now deprecated in lieu of this new, more
  thorough, message).
- The new `RTVIBotOutputMessage` includes the fields:
  - `spoken`: A boolean indicating whether the text was spoken by TTS
  - `aggregated_by`: A string representing how the text was aggregated
    ("sentence", "word", "my custom aggregation")
- Introduced new fields to `RTVIObserver` to support the new
  `bot-output` messaging:
  - `bot_output_enabled`: Defaults to True. Set to false to disable
    bot-output messages.
  - `skip_aggregator_types`: Defaults to `None`. Set to a list of
    strings that match aggregation types that should not be included
    in bot-output messages. (Ex. `credit_card`)
 2025-11-21 17:16:10 -05:00
mattie ruth backman
4f30a48ecd Rime and Cartesia TTS Updates: 
`CartesiaTTSService`:
 - Modified use of custom default text_aggregator to avoid deprecation warnings and push users
   towards use of transformers or the `LLMTextProcessor`
 - Added convenience methods for taking advantage of Cartesia's SSML tags: spell, emotion,
   pauses, volume, and speed.

`RimeTTSService`:
 - Modified use of custom default text_aggregator to avoid deprecation warnings and push users
   towards use of transformers or the `LLMTextProcessor`
 - Added convenience methods for taking advantage of Rime's customization options: spell,
   pauses, pronunciations, and inline speed control.
 2025-11-21 17:16:10 -05:00