dsh-live-voice
Consent-bound one-turn voice preview for DSH Web with a credential-free local synthetic demo, optional Qwen Audio, exact Session isolation, and explicit transcript-to-draft handoff without automatic submission.
DSH Web 的会话绑定单轮语音预览：提供无需凭证的本地合成演示和可选的 Qwen Audio，保持精确会话隔离，并仅在明确操作后将转写写入草稿，不会自动提交。
How to install
dsh plugin add dsh-live-voice About
DSH Live Voice Try it in two minutes · Watch the 24-second demo · Report the stopping point · Preview release DSH Live Voice is built for one bounded voice turn: speak, hear returned audio, review both transcripts, and decide whether to place your own words into the current draft. It never submits the composer or runs tools for you. Unlike a speech-to-text-only microphone button, the intended experience carries native audio in both directions, binds visible consent to the exact live DSH Session, and requires a second explicit action before your transcript enters the draft. Preview.5 adds the e…
Recommendation signals
Meta
- License
- MIT
- Language
- TypeScript
- GitHub stars
- 1
- mo. downloads
- 669
- Last push
- 2026-09-05
- Created
- 2026-08-25
Basic safety check
- Findings
- None
- Sources
- curated:awesome-dsh-plugin.com, curated:awesome-dsh-plugin/awesome-dsh-plugin
- Topics
- ai-assistant, consent, deepseek, deepseek-harness, dsh-plugin, live-voice, microphone, privacy, privacy-first, qwen, react, realtime-audio, speech-to-text, synthetic-audio, typescript, voice, voice-assistant, websocket
Related plugins
dsh-voice-scribe
PensiveFei/dsh-voice-scribe
Voice input for the web UI: tap Alt (or Alt+Space) to start/stop dictation, browser Web Speech (zero-config) or OpenAI-compatible cloud ASR, optional polish through DSH-configured LLM, settings UI.
dsh-tts
GooDAnDReaDY/dsh-tts
Speaks agent replies in the DeepSeek Harness web UI through a provider fallback chain (OpenAI, ElevenLabs, Google, Azure, Groq, Deepgram, OpenRouter, Edge, Piper, eSpeak), so a failing or rate-limited provider falls through to the next instead of going silent.
dsh-ears
WizisCool/dsh-ears
Voice input plugin for DeepSeek Harness (dsh): a microphone button in the composer turns speech into a draft transcript, with a choice of speech-recognition backends, optional polish through dsh own LLM routes, and a native settings page.
dsh-omi-voice
PolinniZhong/dsh-omi-voice
In-chat read-aloud for DeepSeek Harness: tap to read, pause and resume AI replies with natural Doubao TTS voices (BYOK), reading only the final answer with code, tables and diagrams filtered; local engine, plugin keeps no API key.