You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
Repository navigation
Commit ed2fb69
Browse filesBrowse the repository at this point in the historyBrowse files
feat: voice mode on iOS, the home-screen app and Firefox (0.12.0) (#323)
iOS leaves SpeechRecognition out of home-screen web apps (service-not-allowed,
WebKit 225298), Safari's needs Siri and goes deaf after audio plays, and
Firefox has none. Where the browser cannot turn speech into text, voice mode
now records the turn and transcribes it on qrypt.chat.
- voice-recorder.js: RecorderRecognition, a SpeechRecognition look-alike on
getUserMedia + MediaRecorder (webm/opus or iOS mp4) with its own pause
detection from the mic level. The noise floor is calibrated but capped, so
talking the instant the mic opens still counts as speech. The mic is
released after each turn and navigator.audioSession switched to playback so
replies are loud on iPhone; Web Audio is unlocked in the first tap.
- POST /api/voice/transcribe (signed in, 30/min and 1000/day per user, 10000/day
site-wide): passes the clip to Workers AI whisper-large-v3-turbo with the
chat's names as the prompt, drops Whisper's silence phantoms, stores nothing.
Env CF_AI_ACCOUNT_ID / CF_AI_TOKEN.
- Engine choice: iOS always records; elsewhere the browser recognizer, falling
back to recording on service-not-allowed / network / language-not-supported.
- Watchdogs for recognition and speech that never end (iOS), "Hearing you…" /
"Transcribing…" in the bar, and a privacy line per engine.
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
0 commit comments