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`.

```sh
uv sync --extra dev
uv run pytest
```

## Usage

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

```sh
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:

```sh
./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`:

```sh
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_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.