# dsh-voice

> Voice notes in, spoken answers out — dictate audio that becomes user messages (transcribe), have the agent read replies aloud (speak), and leave walk-away narration on long headless runs. Local-first: plain audio files under ~/.dsh/voice/.

## Metadata

- Author: [@Jesse-njx](https://github.com/Jesse-njx)
- Repo: <https://github.com/Jesse-njx/dsh-voice>
- GitHub: [Jesse-njx/dsh-voice](https://github.com/Jesse-njx/dsh-voice)
- Stars: 2
- Language: TypeScript
- License: [MIT](https://spdx.org/licenses/MIT.html)
- Topics: `deepseek-harness`, `dsh-plugin`, `plugin`, `speech-to-text`, `stt`, `text-to-speech`, `tts`, `voice`
- Forks: 0
- Open Issues: 0
- Last push: 2026-08-13T18:02:41.000Z
- Added: 2026-08-14T00:00:00.000Z

## Install

```bash
dsh plugin --profile web add github:Jesse-njx/dsh-voice
```

---

This document is auto-generated by [deepseek-plugin.org](https://deepseek-plugin.org). HTML page: [dsh-voice](https://deepseek-plugin.org/plugins/Jesse-njx/dsh-voice)