> Full usage reference. The landing page focuses on outcomes, installation and workflows; detailed parameters, limits, update rules and historical validation links remain here.

# dsh-voice

[中文](../README.md)

![dsh-voice whale girl plugin cover](https://raw.githubusercontent.com/STARDUSTLC666/dsh-voice/master/assets/cover-whale-girl.png)

Generate speech or transcribe workspace recordings from DSH. Supports Edge TTS and OpenAI, Groq or custom compatible ASR; transcription uses your configured endpoint and output files avoid overwriting by default.

[![npm](https://img.shields.io/npm/v/dsh-voice)](https://www.npmjs.com/package/dsh-voice) [![downloads](https://raw.githubusercontent.com/STARDUSTLC666/dsh-suite/npm-downloads/assets/dsh-voice-downloads.svg)](https://www.npmjs.com/package/dsh-voice) [![total downloads](https://raw.githubusercontent.com/STARDUSTLC666/dsh-suite/npm-downloads/assets/dsh-voice-total-downloads.svg)](https://www.npmjs.com/package/dsh-voice)

[Download statistics](https://github.com/STARDUSTLC666/dsh-suite/blob/npm-downloads/README.md)

Feedback and contributions are welcome: report [issues](https://github.com/STARDUSTLC666/dsh-voice/issues) or submit [pull requests](https://github.com/STARDUSTLC666/dsh-voice/pulls).

## What it does

- Generate speech using the Edge online read-aloud service.
- List voices and generate batch voice previews.
- Transcribe audio using an OpenAI-compatible ASR endpoint.

## Install

In DSH Desktop, install `dsh-voice` from the Plugins panel. If the bundled dsh command is available:

```bash
dsh plugin --profile desktop add dsh-voice
```

For the web version, replace `desktop` with `web`. Restart DSH after installation.

## Start using it

1. Start a DSH session in the workspace where you want the audio saved; ask it to check the voice tools.
2. Provide text, language, voice and speed, for example: “Make a Chinese MP3 from this text; give me a short sample first.”
3. Listen to the sample, generate the complete audio, then play or deliver the returned file.
4. For transcription, configure your own compatible ASR service, provide a local audio file, then review the transcript.

## Requirements and configuration

Speech synthesis requires network access. Transcription needs an ASR endpoint and key. A plugin-specific proxy can be configured.

Detailed configuration, tool arguments and troubleshooting are in the [usage guide](USAGE.en.md). For standalone development, follow the Node requirement in [package.json](../package.json).

## Documentation

- [Usage and troubleshooting](USAGE.en.md)
- [Changelog](../CHANGELOG.md)
- [Validation scope and history](VALIDATION.md)
- [Report a problem or suggest a feature](https://github.com/STARDUSTLC666/dsh-voice/issues)

## Plugin updates

Requires DSH 0.2.1-rc.3 or newer. Update controls sit at the bottom of the existing workbench, or native plugin details for plugins without a workbench. Checks, release notes and preferences expand in place, with no separate update page or settings menu. Automatic checks are on by default; **automatic installation is off by default**. Only explicit opt-in permits compatible stable patches while idle with no unsaved changes. Preferences are independent, with per-plugin disable, deferral and ignore controls. No forced DSH restart or upgrade, and local-source installations stay unchanged. Suite components explain and operate on the whole Suite in the same footer.

Older releases need one manual update in native plugin management to acquire these controls. Publishing to npm does not replace an existing user installation.

## License

Original code: [MIT](../LICENSE). The separate Edge v2 token module is LGPLv3; its source and license are included. See [third-party notices](../THIRD_PARTY_NOTICES.md).