dsh-plugin-tts

## Links - **[中文 README](README.zh.md)**（简体中文） - **[RVC Custom Voice Guide](docs/RVC-GUIDE.md)** — custom voices · chunked progressive playback · compact index · voice packs · portable runtime - **[User Guide (执行手册)](docs/USER-GUIDE.md)** — step-by-step, for first-time users - **[Adaptive chunked playback design](docs/adaptive-chunked-playback.md)** — how gapless long reads work --- # dsh-plugin-tts — Edge TTS + RVC voice for DeepSeek Harness A dual-sided (Host + Web UI) DeepSeek Harness plugin that reads assistant replies aloud — Microsoft Edge's free online TTS out of the box, or **your own RVC voice models** for custom voices. Long replies stream with **gapless adaptive chunked playback**; voices install **one-click from a voice-pack registry**; a **portable RVC runtime** means no RVC WebUI install is needed. > 📖 **First time? See the [user guide (执行手册)](docs/USER-GUIDE.md)** — every step > covers "what / how / how to tell it worked": read-aloud, RVC voices and > voice-pack downloads. ## Features 1. **Read-aloud button** on every finalized assistant message (in the copy / feedback / branch action row): click to speak that message (the button shows an animated equalizer), click again to stop. 2. **Auto-read toggle** in the composer tool row (between the command and the access-mode buttons): when on, every newly completed assistant reply is read aloud automatically (the toggle gets a circular highlight); when off, nothing is auto-read. 3. **Voice settings panel** under 设置 → 插件 → 语音: - **TTS provider**: Edge TTS (free, no API key) / custom RVC voice - **Voice**: 22 live-verified Edge TTS voices (default 晓萱 zh-CN-XiaoxuanNeural) - **Sound tuning**: rate / pitch / volume (0 = default) - **Voice packs**: one-click install of voices from a registry - **Preview**: type text and press the play (triangle) button — a spinning loader shows while it is synthesizing/playing (click again to stop), failures show an inline message. 4. **RVC custom voices**: read with your own trained RVC models, computed locally (upload base audio, index-free mode, advanced params — see the [RVC guide](docs/RVC-GUIDE.md)). 5. **Gapless long reads**: adaptive chunked progressive playback — probe-calibrated chunk size, play-while-converting, Web Audio sample-accurate joins, no gaps between chunks (see the [design doc](docs/adaptive-chunked-playback.md)). ## Requirements - DeepSeek Harness `web` profile (`dsh web`) - Node.js >= 22 (the worker uses the native `WebSocket`) - For **RVC custom voices only**: a local RVC inference environment (an RVC WebUI or the portable runtime) and a running `rvc-server.py`. macOS users: see the [RVC Guide](docs/RVC-GUIDE.md) → "启动本地 RVC 服务" and the [User Guide](docs/USER-GUIDE.md) §4.2. ## Install ```sh # published form: dsh plugin --profile web add "github:1624318455/dsh-plugin-tts#main" # or local development: dsh plugin --profile web add "file:/path/to/dsh-plugin-tts" ``` Restart `dsh web`; the plugin then loads automatically as a profile bundle. ## Voices (live-verified, Edge TTS) | Region | Voices | |---|---| | Simplified Chinese | Xiaoxuan 晓萱 · Xiaoyi 晓伊 · Yunxi 云希 · Yunyang 云扬 · Xiaoxiao 晓晓 · Yunjian 云健 · Yunxia 云夏 · liaoning-Xiaobei 晓北 · shaanxi-Xiaoni 晓妮 | | Taiwan | HsiaoChen 曉臻 · HsiaoYu 曉雨 · YunJhe 雲哲 | | Hong Kong | HiuGaai 曉佳 · HiuMaan 曉曼 · WanLung 雲龍 | | English | Aria · Jenny · Guy · Sonia (UK) | | Other | Nanami 七海 (ja-JP) · SunHi (ko-KR) · Denise (fr-FR) | > Note: legacy voices such as Xiaohan / Xiaomeng / Xiaorui / Xiaoshuang were > removed by the Edge endpoint (`1007 Unsupported voice`) and are not listed. ## Architecture | Layer | Location | Role | |---|---|---| | Host | `lib/index.mjs` | Registers `/dsh-tts-api/speak` (synthesis / chunk queue), `/dsh-tts-audio/` (audio), `/dsh-tts-api/rvc-*` (RVC inference / files / compact index / voice packs) webServer routes; runs a zero-dependency worker via `node -e` | | Client | `lib/client.js` | Hidden `