feat(voice-to-text): on-device speech-to-text (Whisper) - #61
Merged
Conversation
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Transcribe speech to text fully on-device via Whisper (transformers.js / onnxruntime-web, WebGPU->WASM). Record from the mic or upload an audio/video file; audio never leaves the browser (only model weights are fetched from CDN on first use, like the OCR tool). - Models: English Fast (whisper-tiny.en), English Accurate (base.en), Multilingual (base). Model-download progress bar. - Output: editable plain text, inline timestamped view, and SRT/VTT subtitle export from Whisper segment timestamps. Copy + download .txt/.srt/.vtt. Pure tested logic in stt.lib.ts (mixToMono, segmentsToText, time formatters, segmentsToSrt/Vtt). SDK boundary stt.engine.ts (only file touching transformers.js). Audio decode in stt-audio.lib.ts (decodeToMono16k). useAudioRecorder hook (MediaRecorder, typed errors, track cleanup) with tests. transformers chunk added to workbox globIgnores. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Deploying with
|
| Status | Name | Latest Commit | Updated (UTC) |
|---|---|---|---|
| ✅ Deployment successful! View logs |
goodwebtools | 9d956bc | Jul 31 2026, 10:48 PM |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
New Voice to Text tool (
/tools/voice-to-text, Media) — transcribe speech fully on-device.Privacy: audio never leaves the browser; only Whisper model weights are fetched from CDN on first use (same trade-off as the OCR tool).
Engine: transformers.js v4 on onnxruntime-web (dynamically imported; 549KB chunk excluded from PWA precache via globIgnores).
Pure tested logic (
stt.lib.ts), SDK boundary (stt.engine.ts), audio decode (stt-audio.lib.ts),useAudioRecorderhook (tested). Spec+plan underdocs/superpowers/.514 tests pass · lint 0 errors · build green (
/tools/voice-to-textbuilt, no precache bloat).🤖 Generated with Claude Code