audita/README.md

Audita

Audita takes raw audio transcripts and uses an LLM to identify and fix misheard words, jargon, and domain-specific terms.

Development

This project is set up for uv.

uv sync --extra dev
uv run pytest

Usage

Set an OpenRouter API key, then process a transcript with a glossary:

export OPENROUTER_API_KEY=...
uv run audia process transcript.json --glossary glossary.yaml --output corrected.json

Without --output, Audita writes the corrected transcript JSON to stdout and progress logs to stderr.

Useful configuration can be supplied by CLI flag or environment variable:

• AUDITA_MODEL, default openrouter/mistralai/mistral-small-3.2-24b-instruct
• AUDITA_BASE_URL, default https://openrouter.ai/api/v1
• AUDITA_MAX_SECTION_TOKENS, default 16000
• AUDITA_CONFIDENCE_THRESHOLD, default 0.80
• AUDITA_MAX_RETRIES, default 3
• AUDITA_WORK_DIR, default /tmp/audita

AUDITA_WORK_DIR stores per-run diagnostics while processing. Successful runs clean up their run directory; failed runs preserve it for debugging.