wx44wx/pipecat
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

thread simplification + handling interuption

Browse Source
This commit is contained in:
sathwika
2026-04-10 17:18:22 +05:30
parent 8abda808ca
commit 746fadc2b5
3 changed files with 204 additions and 113 deletions
Download Patch File Download Diff File Expand all files Collapse all files

15
changelog/4249.added.md
View File

@@ -1,9 +1,6 @@
- Added cross-sentence stitching support to NvidiaTTSService. Multiple sentences within an LLM turn are fed into a single `SynthesizeOnline` gRPC stream, enabling Magpie's seamless audio across sentence boundaries (requires Magpie TTS model v1.7.0+).
- Added new parameters to NvidiaTTSService:
- `custom_dictionary` for IPA-based custom pronunciation
- `encoding` for output audio encoding format
- `zero_shot_audio_prompt_file` for zero-shot voice cloning with file caching
- `audio_prompt_encoding` for zero-shot audio prompt format
- Added `can_generate_metrics` returning True for NvidiaTTSService.
- Added `stop_all_metrics()` call on audio context interruption.
- Added gRPC error handling for synthesis config retrieval.
- Added enhancements to `NvidiaTTSService`:
- Cross-sentence stitching: multiple sentences within an LLM turn are fed into a single `SynthesizeOnline` gRPC stream for seamless audio across sentence boundaries (requires Magpie TTS model v1.7.0+).
- `custom_dictionary` and `encoding` parameters for IPA-based custom pronunciation and output audio encoding.
- Metrics generation (`can_generate_metrics` returns true) and `stop_all_metrics()` when an audio context is interrupted.
- gRPC error handling around synthesis config retrieval (`GetRivaSynthesisConfig`).

13
changelog/4249.changed.md
View File

@@ -1,5 +1,8 @@
- Updated NvidiaTTSService:
- Made `api_key` optional for local NIM deployments
- Fixed `_update_settings` to correctly indicate that runtime settings updates (voice, language, quality) take effect on the next turn
- Replaced per-sentence synchronous `synthesize_online` calls with async queue-backed gRPC streaming
- Renamed Riva references to Nemotron Speech
- Updated `NvidiaTTSService`:
- Made `api_key` optional for local NIM deployments.
- Voice, language, and quality can be updated without reconnecting the gRPC client; new values take effect on the next synthesis turn, not for the current turn's in-flight requests.
- Replaced per-sentence synchronous `synthesize_online` calls with async queue-backed gRPC streaming.
- Streaming now uses asyncio tasks with explicit gRPC cancellation on interruption and stale-response filtering when a stream is aborted or replaced.
- Renamed Riva references to Nemotron Speech in docs and messages.
- Disabled automatic TTS start frames at the service level (`push_start_frame=False`) and emit `TTSStartedFrame` when a stitched synthesis stream is started for a context.