Skip to content

feat(cloud): fire estimated word boundaries progressively during streaming #14

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
willwade merged 1 commit into from
Aug 16, 2026
Merged

feat(cloud): fire estimated word boundaries progressively during streaming #14

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -29,7 +29,7 @@ Cross-platform TTS (Text-to-Speech) wrapper with C ABI. Mirrors [js-tts-wrapper]
| xAI | Cloud | API Key | Chunked | — | Estimated | Platform-aware |
| ModelsLab | Cloud | API Key | Chunked | — | Estimated | Platform-aware |

- **Streaming**: Audio is delivered through the `on_audio` callback in chunks. REST engines and Edge stream as bytes arrive over the network (MP3 is decoded to PCM16 mono incrementally, on a background reader thread); Azure's WebSocket delivers PCM frames per message. Engines whose APIs return a single JSON document with base64 audio (Google, ElevenLabs `with-timestamps`) deliver only once the response completes — an API limitation. Sherpa-ONNX synthesises the whole clip first, then slices the rendered PCM into 8 KB chunks (matching the cloud delivery shape and the js-tts-wrapper / swift-tts-wrapper siblings).
- **Streaming**: Audio is delivered through the `on_audio` callback in chunks. REST engines and Edge stream as bytes arrive over the network (MP3 is decoded to PCM16 mono incrementally, on a background reader thread); Azure's WebSocket delivers PCM frames per message. Engines whose APIs return a single JSON document with base64 audio (Google, ElevenLabs `with-timestamps`) deliver only once the response completes — an API limitation. Sherpa-ONNX synthesises the whole clip first, then slices the rendered PCM into 8 KB chunks (matching the cloud delivery shape and the js-tts-wrapper / swift-tts-wrapper siblings). Estimated word boundaries (engines without API timing data) fire progressively during streaming, anchored to delivered audio, rather than all at once when the response completes.
- **Native engine varies by platform**: the table shows `system` (Linux speech-dispatcher); macOS uses `avsynth` (AVSpeechSynthesizer) and Windows uses `sapi`. "22 total" counts one native engine + Sherpa-ONNX + the 20 cloud engines, per platform.

## Formatting & Testing
Expand Down
Loading
Loading