1.8 KiB
1.8 KiB
Transcription Options
Ped-AI currently supports server-side transcription plus an explicit browser Web Speech preview option. Browser Whisper was removed and should not be offered in settings, documentation, public workers, or model download scripts.
Recommended Clinical Setup
Use a server-side provider covered by your compliance requirements.
| Need | Recommended provider |
|---|---|
| HIPAA-eligible cloud STT | Google/Gemini through Vertex AI or AWS Transcribe with a BAA. |
| OpenAI-compatible routing | LiteLLM with a compliant upstream. |
| Direct OpenAI Whisper | Only when acceptable for your deployment. |
| Real-time draft preview | Browser Web Speech only with explicit user opt-in and privacy warning. |
Configuration
TRANSCRIBE_PROVIDER=litellm
LITELLM_API_BASE=https://your-litellm.example/v1
LITELLM_API_KEY=<key>
LITELLM_STT_MODEL=whisper-1
Other provider examples:
# Google/Gemini
TRANSCRIBE_PROVIDER=google
GOOGLE_VERTEX_PROJECT=your-project-id
GOOGLE_STT_MODEL=gemini-2.0-flash
# AWS Transcribe
TRANSCRIBE_PROVIDER=aws
AWS_BEDROCK_REGION=us-east-1
AWS_TRANSCRIBE_MEDICAL=true
AWS_TRANSCRIBE_SPECIALTY=PRIMARYCARE
# Direct OpenAI Whisper
TRANSCRIBE_PROVIDER=openai
OPENAI_API_KEY=<key>
Failure Handling
- Server transcription failures can create encrypted audio backups for retry.
- Users can retry or delete failed backups from Settings.
- Web Speech interim text is not a substitute for a server transcription response.
Removed Paths
These should remain absent unless the project intentionally reintroduces browser-local STT with a new design review:
public/js/browserWhisper.jspublic/js/whisperWorker.jspublic/js/whisperWorkerV2.jspublic/models/Xenova/*- Browser Whisper setup/troubleshooting docs
- Whisper model download scripts for public browser models