Commit Graph

26 Commits

Author SHA1 Message Date
Paul Kompfner
f3b254e335 D'oh! My TTS "inter-frame-spaces" logic was *way* overcomplicated (and fundamentally mistaken, though it happened to work)
Now:
- For TTS word-by-word output and `TTSSpeakFrames`: `TTSTextFrame`s' have `includes_inter_frame_spaces=False`.
- For all other TTS output: `TTSTextFrame` pass through the received text frames' `includes_inter_frame_spaces` value. So far, this value has always been `True`: LLMs send text chunks already containing all necessary spaces.
- `LLMTextFrame`s set `includes_inter_frame_spaces=False` at init time, per the aforementioned assumption.
2025-11-17 10:14:28 -05:00
Angad Singh
d1116d149e feat: Add ErrorFrame emission to TTS/STT services for pipeline error detection (#2881)
* feat: Add ErrorFrame emission to TTS/STT services for pipeline error detection

- Add ErrorFrame emission to all major TTS/STT services during initialization and runtime failures
- Services updated: Cartesia, ElevenLabs, Deepgram, AssemblyAI, Rime, Azure
- ErrorFrame objects emitted with fatal=False for graceful degradation
- Enables on_pipeline_error event handler to detect service failures programmatically
- Add comprehensive pytest test suite to verify ErrorFrame emission
- Fixes issue where services failed gracefully but didn't emit ErrorFrame objects

This allows developers to implement real-time error monitoring and alerting
using the on_pipeline_error event handler introduced in v0.0.90.

* Update STT and TTS services to use consistent error handling pattern

- Improves error handling consistency across all services

* Add changelog entry for STT/TTS error handling improvements

* Linting issues Resolved

* Azure STT ErrorFrames added with consistent patterns

* Cartesia STT and Deepgram STT; additional fixes made

* Removed Fatal Flags across services, removed duplication

* Moving the changelog entry to the correct place.

* Refactoring some classes to use yield instead of push_error directly.

* Fixing ruff format.

---------

Co-authored-by: Filipi Fuchter <filipi87@gmail.com>
2025-11-14 15:03:05 -03:00
kompfner
e83ac82bf3 Merge pull request #3042 from pipecat-ai/pk/follow-up-inter-frame-spaces
Follow-up to #3041
2025-11-13 11:03:06 -05:00
Mark Backman
edbf96b3c5 Update GeminiTTSService for streaming, other Google TTS improvements 2025-11-13 10:22:34 -05:00
Paul Kompfner
1ad6405ebb Override includes_inter_frame_spaces in:
- `GoogleHttpTTSService`
- `OpenAITTSService`

The reason I skipped this work in an earlier PR was because these services seemed to be emitting long, punctuation-free text frames. It turns out that the issue was with the LLM prompt, though, resulting in the LLM nondeterministically excluding all punctuation. An upcoming commit will address that prompt issue.
2025-11-12 17:07:43 -05:00
Paul Kompfner
5222ff99de Apply includes_inter_frame_spaces = True in all LLM and TTS services that need it.
Note that for `LLMTextFrame`s, the right behavior is pretty much always `includes_inter_frame_spaces = True`. I decided *not* to go ahead and make that the default for `LLMTextFrame`s, though, simply to not introduce a subtle behavior change for creative/unexpected use-cases that were relying on text in hand-crafted `LLMTextFrame`s being handled a certain way. Ditto for `TTSTextFrame`s.

Also, fix an issue in `NeuphonicTTSService` where it wasn't pushing `TTSTextFrame`s.

Also, fix the broken `SarvamHttpTTSService` example.

Also, add a couple of missing examples.
2025-11-12 15:10:11 -05:00
Mark Backman
2ee54c985f Improve language checking in STT and TTS services 2025-11-05 12:26:52 -05:00
Thu Nguyen
6ade5617fb addressed comments 2025-10-31 09:53:47 +07:00
Thu Nguyen
057e0c3973 Lint 2025-10-30 17:12:36 +07:00
Thu Nguyen
8a6abdd44b feat: Add dynamic speaking_rate control for Google TTS Chirp voices 2025-10-30 17:09:41 +07:00
Manish Kumar
4699ee8d86 docs: add docstring for voice_cloning_key and update CHANGELOG 2025-09-04 22:45:51 +05:30
Manish Kumar
2ee481d541 feat: add voice cloning and speaking rate to GoogleTTSService 2025-08-30 23:04:59 +05:30
Mark Backman
541a43905b Add GeminiTTSService 2025-08-12 14:52:20 -04:00
Mark Backman
fd570b0377 Update the remaining docstrings, update pre-commit hook, add docstring formatting CI, update CONTRIBUTING with formatting guidance (#2089) 2025-07-01 00:37:04 -04:00
Mark Backman
0ecfa827e6 Improve docstrings for services and processors (#2087) 2025-06-28 13:39:45 -04:00
Aleix Conchillo Flaqué
901dd041f0 buffer audio from TTS service before pushing frames 2025-06-09 07:29:09 -07:00
unknown
d3e2a9e5c0 Change default voice and fix formatting 2025-05-24 15:14:39 +02:00
unknown
bfe9952c9a Remove sleep(0), add doc string etc. 2025-05-23 12:11:08 +02:00
unknown
d42d02d809 Add Google streaming TTS as a base TTS service. Rename non-streaming service to GoogleHttpTTSService. 2025-05-22 11:21:06 +02:00
Aleix Conchillo Flaqué
a09bd648af avoid mutable default constructor values 2025-05-20 11:59:28 -07:00
Mark Backman
50f6235edb Add support for OpenTelemetry tracing (#1729)
* Also added TurnTrackingObserver, TurnTraceObserver, foundational 29, open-telemetry-example
2025-05-13 17:18:11 -04:00
Mark Backman
70c42dfa6e Merge pull request #1525 from shaiyon/google-default-creds
Enable usage of Application Default Credentials in Google services
2025-04-18 11:31:08 -04:00
Aleix Conchillo Flaqué
6cea71270e tts: use smaller audio chunk sizes 2025-04-16 14:40:59 -07:00
Shaiyon Hariri
af23200511 Use default google creds as fallback when not provided in llm_vertex,stt, and tts 2025-04-03 16:42:58 -04:00
Aleix Conchillo Flaqué
9eba8f1637 services: restructure base AI services into modules 2025-03-31 13:53:36 -07:00
Aleix Conchillo Flaqué
3074a62bb1 services: restructure services into folders 2025-03-30 16:21:00 -07:00