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 audita process transcript.json --glossary glossary.yaml --output corrected.json

From a checked-out repository, you can also use the root launcher:

./audita process transcript.json --glossary glossary.yaml --output corrected.json

For a system-wide command, install the source tree under /usr/local/src/audita, sync dependencies there, and symlink the root launcher into your PATH:

cd /usr/local/src/audita
uv sync --extra dev
ln -s /usr/local/src/audita/audita /usr/local/bin/audita
audita 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_GLOSSARY_MAX_LLM_PASSES, default 3, for total glossary correction passes
AUDITA_WORK_DIR, default /tmp/audita

AUDITA_WORK_DIR stores per-run diagnostics while processing. Successful runs clean up their run directory unless corrections are skipped for target mismatches; failed runs and skipped-correction runs preserve diagnostics for debugging.