wx44wx/pipecat
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
6,395 Commits 276 Branches 111 Tags
e1528d0f0c737a43d68099d0f29cea5a9a9328f5
Commit Graph

6395 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
mattie ruth backman
e1528d0f0c Added support to TTS services to skip sending text to the... 
the actual TTS service to be spoken based on its aggregation type.
 2025-11-21 17:16:10 -05:00
mattie ruth backman
6b6d760cf1 Introduced LLMTextProcessor and deprecatd custom text_aggregators in TTS 
Introduced `LLMTextProcessor`: A new processor meant to allow customization for how
LLMTextFrames should be aggregated and considered. It's purpose is to turn
`LLMTextFrame`s into `AggregatedTextFrame`s. By default, a TTSService will still
aggregate `LLMTextFrame`s by sentence for the service to consume. However, if you
wish to override how the llm text is aggregated, you should no longer override the
TTS's internal text_aggregator, but instead, insert this processor between your LLM
and TTS in the pipeline.
 2025-11-21 17:16:10 -05:00
mattie ruth backman
7a4372a909 Introduced a new AggregatedTextFrame Frame type that TTSTextFrame inherits from 
This frame introduces an `aggregated_by` field to describe the type of text included
in the frame and allows unspoken groupings of text to be pushed through the pipeline
and treated similar to TTSTextFrames.
 2025-11-21 17:16:10 -05:00
mattie ruth backman
0e820a01b9 Introduce append_to_context to TextFrames 
Adding support for setting whether or not the text in the TextFrame
should be added to the LLM context (by the LLM assistant aggregator).
Defaults to `True`.
 2025-11-21 17:16:10 -05:00
mattie ruth backman
24266c238f Augmented PatternPairAggregator so that matched patterns can... 
be treated as their own aggregation, taking advantage of the new
ability to assign a type to an aggregation
 2025-11-21 17:16:10 -05:00
mattie ruth backman
dcc20f86e1 Updated the BaseTextAggregator to categorize aggregations 
Modified the BaseTextAggregator type so that when text gets aggregated, metadata can
be associated with it. Currently, that just means a `type`, so that the aggregation
can be classified or described. Changes made to support this:
  - **IMPORTANT**: Aggregators are now expected to strip leading/trailing white space
    characters before returning their aggregation from `aggregation()` or `.text`. This
    way all aggregators have a consistent contract allowing downstream use to know how
    to stitch aggregations back together
  - Introduced a new `Aggregation` dataclass to represent both the aggregated `text` and
    a string identifying the `type` of aggregation (ex. "sentence", "word", "my custom
    aggregation")
  - **BREAKING**: `BaseTextAggregator.text` now returns an `Aggregation` (instead of `str`).
    To update: `aggregated_text = myAggregator.text` -> `aggregated_text = myAggregator.text.text`
  - **BREAKING**: `BaseTextAggregator.aggregate()` now returns `Optional[Aggregation]`
    (instead of `Optional[str]`). To update:
      ```
      aggregation = myAggregator.aggregate(text)
      if (aggregation):
        print(f"successfully aggregated text: {aggregation.text}") // instead of {aggregation}
      ```
  - `SimpleTextAggregator`, `SkipTagsAggregator`, `PatternPairAggregator` updated to
     produce/consume `Aggregation` objects.
  - All uses of the above Aggregators have been updated accordingly.
 2025-11-21 17:16:10 -05:00
Vanessa Pyne
26918728df Merge pull request #3096 from pipecat-ai/vp-minimax-2962-v2 
minimax 2962 language updates
 2025-11-20 10:41:35 -06:00
vipyne
954849379b cleanup 2025-11-20 10:41:09 -06:00
vipyne
06542a2dbc Update CHANGELOG 2025-11-20 10:41:09 -06:00
Vanessa Pyne
59d40eac45 Update src/pipecat/services/minimax/tts.py 
Co-authored-by: Mark Backman <mark@daily.co>

add warning
 2025-11-20 10:41:09 -06:00
vipyne
17cf6c56cf minimax updates 
some `debug`s -> `trace`s

add western US base_url to docs

ensure error_message is defined

add deprecation warning for `english_normalization` param
 2025-11-20 10:41:09 -06:00
minimax
616e6ba351 docs(minimax): add API endpoint comment for west US region 2025-11-20 10:41:08 -06:00
minimax
f3cb5e0106 feat(minimax): comprehensive updates to TTS service 
- Add support for speech-2.6-hd and speech-2.6-turbo models
- Add 16 new languages (total 40): Afrikaans, Bulgarian, Catalan, Danish, Persian, Filipino, Hebrew, Croatian, Hungarian, Malay, Norwegian, Nynorsk, Slovak, Slovenian, Swedish, Tamil
- Add new emotions: calm and fluent
- Add new parameters: text_normalization (renamed from english_normalization), latex_read, force_cbr, exclude_aggregated_audio, subtitle_enable, subtitle_type
- Extract trace_id from response headers for all requests
- Improve error handling for non-streaming error responses
- Add detailed extra_info logging (audio_length, audio_size, usage_characters, word_count)
- Add validation warnings for language/model compatibility
- Fix silent error issue where HTTP 200 responses with errors were ignored

BREAKING CHANGE: Renamed parameter english_normalization to text_normalization
 2025-11-20 10:41:08 -06:00
Aleix Conchillo Flaqué
c89f230c99 fix CHANGELOG 2025-11-20 08:40:30 -08:00
Aleix Conchillo Flaqué
69cd5716cd Merge pull request #3102 from pipecat-ai/aleix/daily-python-0.22.0 
pyproject: update daily-python to 0.22.0
 2025-11-20 08:35:39 -08:00
Mark Backman
ab58f72322 Merge pull request #3101 from hwuiwon/hw/inworld-talking-speed 
feat: Add speaking rate control to Inworld TTS service.
 2025-11-20 09:50:55 -05:00
Hwuiwon Kim
ead361f665 fix 2025-11-20 07:45:13 -05:00
Aleix Conchillo Flaqué
fa6b8851ed pyproject: update daily-python to 0.22.0 2025-11-19 21:56:38 -08:00
Hwuiwon Kim
1cc69d475d feat: Add speaking rate control to Inworld TTS service & fix param cases 2025-11-19 22:57:53 -05:00
Mark Backman
51bdd8b728 Merge pull request #3097 from hwuiwon/fix-typo 
Fix typo in STT event handler documentation
 2025-11-19 17:10:32 -05:00
Hwuiwon Kim
30ff488714 Fix typo in event handler documentation 2025-11-19 17:04:07 -05:00
Vanessa Pyne
510f3df6b7 Merge pull request #3091 from pipecat-ai/vp-fix-mcp-examples 
update MCP foundational examples
 2025-11-19 10:35:08 -06:00
vipyne
68292bd75f rename MCP foundational examples 2025-11-19 10:34:13 -06:00
vipyne
42423bff41 update MCP foundational examples 2025-11-19 10:29:18 -06:00
Aleix Conchillo Flaqué
c3d2a25229 Merge pull request #3082 from pipecat-ai/aleix/pipecat-0.0.95 
update CHANGELOG for 0.0.95
v0.0.95 		2025-11-18 21:17:07 -08:00
Aleix Conchillo Flaqué
cf1a9c1548 update CHANGELOG for 0.0.95 2025-11-18 21:14:27 -08:00
Aleix Conchillo Flaqué
51ba245e10 scripts(evals): fix EVAL_CONVERSATION/EVAL_WEATHER eval 2025-11-18 21:14:27 -08:00
Aleix Conchillo Flaqué
39b4e61837 SimliVideoService: fix connection issue 2025-11-18 19:41:47 -08:00
Aleix Conchillo Flaqué
ceaf53fdb0 LLMContext: async create_image_message/create_audio_message fixes 2025-11-18 19:41:13 -08:00
Aleix Conchillo Flaqué
f93276c64f Merge pull request #3090 from pipecat-ai/revert_function_calling_pr 
Reverting: Ensure that the function call results respect the previous LLM context
 2025-11-18 19:40:58 -08:00
Mark Backman
62a0f0c0f5 Merge pull request #3070 from ivaaan/hume-timestamps 2025-11-18 19:56:20 -05:00
Filipi Fuchter
793aca6b8b Revert "Ensure that the function call results respect the previous LLM context." 
This reverts commit a510b276e6.
 2025-11-18 21:38:49 -03:00
Filipi Fuchter
1fcaf3a4bf Revert "Searching in both _function_calls_context_messages and context messages when updating the result." 
This reverts commit fccc91e923.
 2025-11-18 21:38:49 -03:00
ivaaan
6484855139 fix changelog 2025-11-18 21:47:46 +01:00
ivaaan
771469b834 fix changelog 2025-11-18 21:39:29 +01:00
kompfner
a60618b0ca Merge pull request #3080 from pipecat-ai/pk/assistant-aggregator-handles-mixed-includes-inter-frame-spaces-text 
`LLMAssistantAggregator` now properly aggregates text that might be a…
 2025-11-18 15:24:27 -05:00
Paul Kompfner
3d21faaac2 LLMAssistantAggregator now properly aggregates text that might be a mix of includes_inter_frame_spaces=True and includes_inter_frame_spaces=False frames 2025-11-18 15:12:25 -05:00
ivaaan
f325eeb95b rm TranscriptProcessor 2 2025-11-18 20:41:10 +01:00
ivaaan
4c3fd42b1c fix changelog 2025-11-18 20:36:45 +01:00
ivaaan
c2309efd7e rm TranscriptProcessor 2025-11-18 20:35:09 +01:00
Ivan A
4ae1819645 Update src/pipecat/services/hume/tts.py 
Co-authored-by: Mark Backman <m.backman@gmail.com>
 2025-11-18 20:30:44 +01:00
Ivan A
a38f208135 Update examples/foundational/07ae-interruptible-hume.py 
Co-authored-by: Mark Backman <m.backman@gmail.com>
 2025-11-18 20:30:28 +01:00
Mark Backman
d1eb837890 Merge pull request #3081 from pipecat-ai/mb/fix-30-tts-text-frame-log 
Fix foundational 30 example to output TTSTextFrames synced to audio
 2025-11-18 14:10:56 -05:00
Mark Backman
153201542b Fix foundational 30 example to output TTSTextFrames synced to audio 2025-11-18 13:29:06 -05:00
Filipi da Silva Fuchter
9137e50043 Merge pull request #3053 from pipecat-ai/filipi/function_calls 
Ensure that the function call results respect the previous LLM context.
 2025-11-18 14:59:01 -03:00
Ivan A
8dbe119a73 Merge branch 'main' into hume-timestamps 2025-11-18 18:38:24 +01:00
ivaaan
26f96d0be8 upd example 2025-11-18 18:31:38 +01:00
ivaaan
9944e6faf0 upd service based on Mark's suggestions 2025-11-18 18:25:53 +01:00
Aleix Conchillo Flaqué
c1573c1f76 Merge pull request #3078 from pipecat-ai/aleix/llm-context-create-image-audio-async 
LLMContext: create_image_message/create_audio_message are now async
 2025-11-18 09:06:51 -08:00
Aleix Conchillo Flaqué
9f45ad4d2e LLMContext: create_image_message/create_audio_message are now async 2025-11-18 09:04:40 -08:00