Back to catalog

GITHUB TOPIC

speech-to-text

41projects include this topic

The "speech-to-text" topic on GitHub groups 41 open-source projects in the DeepSeek Harness (DSH) ecosystem, led by dsh-voice-prompt-enhancer with 125 GitHub stars. dsh-voice-prompt-enhancer — DeepSeek Harness (DSH) plugin: one-click prompt enhancement + speech recognition (auto-stop after speaking · cloud/local dual engine) · includes one-click restart on service errors. Every project here is indexed by DSH Universe with live GitHub data — stars, activity and install status — so you can compare and install directly.

{count} projects

Exact GitHub Topic match

Agents & sessionsPlugin

DeepSeek Harness (DSH) plugin: ✨ one-click prompt enhancement + 💬 speech recognition (auto-stop after speaking · cloud/local dual engine) · includes 🔁 one-click restart on service errors

Structure check pending
ai-plugindeepseekdeepseek-harnessdsh
DSH PluginsPlugin

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.

Structure check pending
asrdeepseek-harnessdsh-pluginspeech-to-text
LifestylePlugin

dsh-ears

WizisCool

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

Structure check pending
asrdeepseek-harnessdshdsh-plugin
LifestylePlugin

dsh-voice-mode

qishuilalala

DSH full-duplex voice conversation mode: streaming zipformer2 recognition into an editable draft, optional wake word, Edge TTS sentence-by-sentence reading + real-time subtitles, barge-in on speech, no API Key needed. Full-duplex voice mode for DeepSeek Harness, no API key.

Structure check pending
asrbarge-incaptionsdeepseek-harness
LifestylePlugin

dsh-talk

PerryLink

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.

Structure check pending
cordisdeepseekdeepseek-harnessdsh
DSH PluginsPlugin

Local-first voice conversations for DSH. Run speech recognition and speech synthesis on your own machine, with optional external providers.

Structure check pending
deepseek-harnessdshdsh-plugindsh-plugins
LifestylePlugin

dsh-voice

Jesse-njx

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/.

Structure check pending
deepseek-harnessdsh-pluginpluginspeech-to-text
DSH PluginsPlugin

dsh-locale-russian

nemezida1337

Русская локализация DeepSeek Harness: перевод интерфейса, описания плагинов и локальный русский голосовой ввод (GigaAM v3)

Structure check pending
cordisdeepseekdeepseek-harnessdsh-plugin
LifestylePlugin

voco-input-sh

Nothree-code

DeepSeek Harness (dsh web) voice input plugin: integrates VocoType local offline recognition, results auto-inserted into the chat input box (auto-deploy/anti-duplication/continuous input)

Structure check pending
asrdeepseek-harnessdshdsh-plugin
LifestylePlugin

Give a DeepSeek Harness agent a voice it owns — offer_call rings the human (answer/decline/later); local TTS via CrispASR + Qwen3-TTS CustomVoice, 9 speakers, 2 Chinese dialects. Local-first, offline-capable.

Structure check pending
ai-agentcrispasrdeepseek-harnessdsh-plugin
Models & MCPPlugin

Hands-free Italian/English voice conversations for DSH, with automatic prompts, an inline chat dock and optional local speech models.

Structure check pending
dshdsh-pluginitalianlocal-ai
LifestylePlugin

dsh-voice

zhuiyueya

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

Structure check pending
ai-agentsdeepseekdeepseek-harnessdeepseek-harness-plugin
DSH PluginsPlugin

Continuous voice dialog for DeepSeek Harness: one microphone, auto-read replies, soft steering interruptions

Structure check pending
deepseek-harnessdshdsh-pluginspeech-to-text
LifestylePlugin

dsh-voice-mic

Zachary7456

DeepSeek Harness (dsh) voice input plugin: record with mic button/hotkey, real-time transcription backfilled into the input box. Three recognition engines: browser Web Speech, local SenseVoice/Paraformer offline backend (one-click deploy), OpenAI-compatible cloud ASR API.

Structure check pending
asrdeepseek-harnessdsh-pluginfunasr
LifestylePlugin

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

Structure check pending
asraudiodeepseek-harnessdsh
DSH PluginsPlugin

Independent DeepSeek Harness voice-input bundle: browser recording transcribed by a local SpeechRail service or any other loopback OpenAI-compatible engine. Capability-snapshot aware, three-state credential verdict, single in-flight gate, agent-facing status tool. Loopback only.

Structure check pending
asrcordisdeepseek-harnessdictation
LifestylePlugin

Voice input plugin for DeepSeek Harness with live microphone metering and manual stop/cancel controls.

Structure check pending
deepseek-harnessdsh-pluginspeech-to-textvoice-input
DSH PluginsPlugin

DeepSeek Harness global plugin for MiniMax speech recognition (asr-1.0): transcribe_audio tool + settings card + voice input in the input box

Structure check pending
asrasr-modeldeepseek-harnessdeepseek-harness-plugin
LifestylePlugin

dsh-voice

motongv

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

Structure check pending
deepseekdeepseek-harnessdshdsh-plugin
DSH PluginsPlugin

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

Structure check pending
cordisdeepseekdeepseek-harnessdictation
DSH PluginsPlugin

dsh-asr-voice

bitterSmilezzz

Speak and it's written · Speak-to-prompt for DeepSeek Harness: cloud ASR speech recognition + Prompt optimization + fill into draft/auto send, cross-platform macOS / Windows.

Structure check pending
asrdeepseek-harnessdshdsh-plugin
LifestylePlugin

dsh-voice

charlie-pan

🎤 DeepSeek Harness speech-to-text plugin: mic button at the bottom right of the input box, three engines (browser built-in / iFlytek / local Whisper), microphone device selection, auto gain, liquid glass style.

Structure check pending
deepseek-harnessdshdsh-pluginspeech-to-text
CommunicationChannel integration

dsh-hold-to-talk

Gammonmush803

Hold-to-talk voice input for DeepSeek Harness Web, runs locally with SenseVoice via sherpa-onnx, offline, no API key.

Structure check pending
asraudiodeepseek-harnessdictation
LifestylePlugin

DSH voice input plugin: tap the mic and speak, text goes into the input box automatically. Local Whisper engine, designed for non-typists. Voice-to-text plugin for DeepSeek Harness.

Structure check pending
deepseek-harnessdsh-pluginspeech-to-textvoice-input
LifestylePlugin

dsh-voice-input

juexiongchen-boop

DeepSeek Harness input box voice input plugin: local sherpa-onnx streaming recognition (Chinese-English bilingual + punctuation), mic button / live captions / sentence fill-back / auto-close after 3s silence

Structure check pending
deepseek-harnessdsh-pluginsherpa-onnxspeech-to-text
LifestylePlugin

No project description provided yet.

Structure check pending
ai-agentscordisdeepseekdeepseek-ai
LifestylePlugin

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

Structure check pending
deepseek-harnessdsh-pluginkokorospeech-to-text
LifestylePlugin

Locally deployed small speech model

Structure check pending
deepseek-harnessdictationdsh-pluginlocal-first
InterfacePlugin

dsh-voice

lucagiftzek

Read-aloud, dictation and language-aware speech for the DeepSeek Harness web UI: 23 TTS and STT providers, per-language routing, word highlighting.

Structure check pending
deepseek-harnessdictationdshdsh-plugin
DSH PluginsPlugin

dsh-voice-ext

machine202502

Local Russian speech recognition for DeepSeek Harness: GigaAM v3 via sherpa-onnx, fully offline

Structure check pending
cordisdeepseek-harnessdshdsh-plugin
DSH PluginsPlugin

Offline local speech-to-text for the DeepSeek Harness composer: a microphone button that records, transcribes with faster-whisper on your own machine, and inserts the text into the chat draft.

Structure check pending
cordisdeepseekdeepseek-harnessdsh
DSH PluginsPlugin

Chat with DSH like an IM call while it watches your screen: token-efficient sampling, a floating chat window, mid-turn messages, and a listen-only mode. Working toward the plugin deciding for itself when to look and when to listen - not there yet. Windows 10 + DSH 0.2.2-rc.1 only; mic input untested.

Structure check pending
deepseekdshdsh-pluginffmpeg
DSH PluginsPlugin

dsh-voz-es

navasfj

Local Spanish voice for DeepSeek Harness: Whisper dictation and Piper text-to-speech, 100% on-device.

Structure check pending
deepseek-harnessdsh-pluginofflinepiper
Development toolsPlugin

dsh-voice

navid-kianfar

Dictate prompts into the DeepSeek Harness Web Client — a microphone in the composer, with swappable transcription: hosted Whisper API, self-hosted server, or a fully offline whisper.cpp binary.

Structure check pending
cordisdeepseek-harnessdeepseek-harness-plugindeepseek-harness-plugins
DSH PluginsPlugin

DSH 0.2 桌面版语音插件(dsh-voice-mode 的非官方兼容分支):流式识别入草稿、按句朗读 + 实时字幕、开口即打断,另含 ASR 纠错词表与整段丢字修复。 · Unofficial dsh-voice-mode port for the DSH 0.2 desktop app: streaming ASR into the draft, per-sentence TTS with live captions, true barge-in, plus a local ASR correction dictionary.

Structure check pending
asrbarge-incaptionschinese
Models & MCPPlugin

Local Russian speech-to-text provider for DeepSeek Harness voice input: NVIDIA Nemotron 3.5 ASR 0.6B (GGUF) on transcribe.cpp. Model and native runtime download on first use, sha256-verified.

Structure check pending
asrdeepseek-harnessdshdsh-plugin
LifestylePlugin

dsh-doubao-voice

Vorpal-poem

DeepSeek Harness voice input plugin: Volcengine streaming ASR (Doubao Seed ASR), streams back into the input box. Voice input for DSH via Volcengine streaming ASR.

Structure check pending
asrdeepseekdeepseek-harnessdeepseek-harness-plugin
DSH PluginsPlugin

dsh-voice

wencharmwang

plugin of voice input for DeepSeek Harness

Structure check pending
deepseek-harnessdsh-pluginspeech-to-textwhisper
LifestylePlugin

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

Structure check pending
chromiumdeepseekdeepseek-harnessdictation
DSH PluginsSkill

dsh-voice

xh0915

鲸歌 · 把文字读成声音,把录音听写成文字 · DeepSeek Harness 语音技能

Structure check pending
deepseek-harnessdsh-skillpythonspeech-to-text
LifestylePlugin

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

Structure check pending
deepseek-harnessdsh-pluginelevenlabsspeech-to-text