Speak Fill

Voice-dictated form filling — build a form, then fill it out by talking. Speech is transcribed locally and in real time by faster-whisper (no cloud STT service), and an LLM maps what you said onto the right form fields.

Install

pip install speakfill
speakfill

Opens at http://localhost:8000 — one process serves both the API and the UI, backed by a local SQLite database at ~/.speakfill/speakfill.db. No Docker, no separate database required.

Set OPENAI_API_KEY for whole-form dictation's LLM field-mapping (or LLM_PROVIDER=local, see below, to use a local model instead). Per-field dictation and speech-to-text need no API key at all.

Extras

• pip install speakfill[postgres] — use Postgres instead of the default SQLite (DATABASE_URL=...)
• pip install speakfill[local-llm] — run field-mapping locally instead of via OpenAI (LLM_PROVIDER=local); pulls in torch/transformers

Links

Full documentation, architecture notes, and source: https://github.com/mohpezeshki/speak-fill