> ## Documentation Index
> Fetch the complete documentation index at: https://docs.10et.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# tenet voice

> Voice input — record, transcribe, classify, and route to projects

Record voice notes, transcribe them, classify topics, and route insights to the right project journals.

## Usage

```bash theme={null}
# Start recording
tenet voice

# Log a voice note from a file
tenet voice log ~/Desktop/meeting.m4a

# Ingest and classify a recording
tenet voice ingest ~/Desktop/call.m4a

# Watch a folder for new recordings (iCloud sync)
tenet voice watch ~/Library/Mobile\ Documents
```

## Commands

| Command                     | Description                                              |
| --------------------------- | -------------------------------------------------------- |
| `tenet voice`               | Start recording from microphone                          |
| `tenet voice log <file>`    | Transcribe and log a voice file                          |
| `tenet voice ingest <file>` | Full pipeline: transcribe → classify → route to projects |
| `tenet voice watch <dir>`   | Watch a directory for new audio files                    |

## Options

| Flag                | Description            |
| ------------------- | ---------------------- |
| `-d, --device <id>` | Audio device ID to use |
| `-h, --help`        | Display help           |

## How It Works

1. **Record** — captures audio from mic or ingests a file
2. **Transcribe** — sends to Groq/Gemini for fast transcription
3. **Classify** — two-pass LLM classification (topic clustering → product assignment)
4. **Route** — classified items go to the right project journals

Voice notes become searchable journal entries. A 45-minute call becomes 9 classified insights in \~3 minutes.

## See Also

* [Getting Started](/quickstart)
* [Memory System](/memory/overview)