speech-to-text

DSH voice input plugin: tap Alt to talk, get text in composer. Web Speech default (zero config), optional OpenAI-compatible ASR, polish via DSH LLM.

Voice input plugin for DeepSeek Harness (DSH) with text polishing. Supports local GPU Whisper and STT(ASR) API | 一款支持润色整理的 DeepSeek Harness 语音输入插件，为 DSH 提供语音输入能力，支持本地 GPU Whisper 和主流语音识别转写 API

Voice-first session loop for DeepSeek Harness: a composer microphone button with browser/local speech-to-text (Web Speech, FunASR, whisper.cpp), a speak tool for text-to-speech replies (browser, edge-tts, piper), event announcements with mute, and speak-to-interrupt.

Give a DeepSeek Harness agent a voice it owns — offer_call rings the human (接听/拒接/稍后); local-first TTS/STT via CrispASR + Qwen3-TTS (9 voices, 2 CN dialects). DSH 0.1.2-rc.1 compatible. Fork of dsh-voice.

Real-time voice input and spoken answer summaries for DeepSeek Harness.

Voice input plugin — a mic button in the composer tool row that turns speech into text live via the browser's Web Speech API (Chrome/Edge), with language switching and optional auto-send. Zero dependencies.

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/.

Voice for DeepSeek Harness（dsh） — speech-to-text input + read-aloud TTS for text-only DeepSeek, zero API key.

DeepSeek Harness (dsh web) 语音输入插件：集成 VocoType 本地离线识别，识别结果自动插入聊天输入框（自动部署/防重复/持续输入）

开口即成文 · Speak-to-prompt for DeepSeek Harness：云端 ASR 语音识别 + 提示词优化 + 填入草稿/自动发送，跨平台 macOS / Windows。

Voice for the DeepSeek Harness: speak to the agent, hear it back, and see what it is doing from a floating window that stays on top of whatever you are running.

DeepSeek Harness (dsh) 语音输入插件：麦克风按钮/快捷键录音，实时转写回填输入框。三种识别引擎：浏览器 Web Speech、本地 SenseVoice/Paraformer 离线后端（一键部署）、OpenAI 兼容云端 ASR API。

Voice input + Edge-TTS read-aloud plugin for DeepSeek Harness

Audio Copilot for DeepSeek Harness — transcribe audio (ASR) , with an in-composer voice-input mic button. 🎤

为 DeepSeek Harness 提供语音输入，支持实时麦克风音量显示，以及手动停止和取消控制。Voice input plugin for DeepSeek Harness with live microphone metering and manual stop/cancel controls.

语音输入插件 for Deepseek Harness

安全版本地语音输入插件 for DeepSeek Harness:同源宿主代理 + 127.0.0.1 + token,SenseVoice-Small INT8 ONNX 本地转写,音频不出网。

Minimal, English-only voice input plugin for DeepSeek Harness Web UI — a mic button in the composer using the browser's native SpeechRecognition API. Zero dependencies, no subprocess, no tracking.

DeepSeek Harness 语音输入：本地多语言识别与 Codex Desktop 听写，只写入可编辑草稿。

🎤 DeepSeek Harness 语音转文字插件：输入框右下角麦克风按钮，浏览器自带 / 讯飞 / 本地 Whisper 三种引擎，麦克风设备选择，自动增益，液态玻璃风格。

plugin of voice input for DeepSeek Harness

Push-to-talk voice dictation for DeepSeek Harness: mic button in the composer transcribes via local Parakeet STT into your message draft

DSH 语音输入插件：点一下麦克风说话，文字自动进输入框。本地 Whisper 引擎，为打字小白设计。Voice-to-text plugin for DeepSeek Harness.

DeepSeek Harness 输入框语音输入插件：本地 sherpa-onnx 流式识别（中英双语+标点），麦克风按钮/实时字幕/断句回填/3 秒静音自动关闭

该仓库暂未提供项目说明。

Local voice plugin for DeepSeek Harness: microphone dictation with local STT plus assistant-response Kokoro TTS playback.

本地部署小语音模型

DeepSeek Harness 语音输入插件：火山引擎流式 ASR（豆包 Seed ASR），流式回填输入框。Voice input for DSH via Volcengine streaming ASR.

Local, offline voice input for DeepSeek Harness -Parakeet and NeMo-Speech.cpp

Local voice typing and speech-to-text plugin for DeepSeek Harness (dsh), powered by multilingual Whisper.

Voice mode for DeepSeek Harness: live captions, push-to-talk, spoken agent replies, barge-in, and real thread control via ElevenLabs.