Upstar existe aussi en français.

Voir cette page en français

Upstar ranks the fastest-rising GitHub projects every hour, across 69 topics. Browse topics

#speech-to-text · AI & ML

Speech-to-text

Speech recognition, transcription and dictation, from open models to local apps.

This month (Oct 4 – Nov 2), the top-ranked are hex (+3,556), VoiceStudio (+46,196) and PixelBoard (+1,289). The 248 ranked repos gained 99,746 stars.

Updated Nov 2, 12:33 UTC · ranked every hour from GitHub’s daily star counts

Updated 51 min ago

GitHub topic ↗ (opens in new tab)

This month’s ranking

Showing 90 of 248

How Upstar ranks

  1. 1
    anomalyco/hex Local voice dictation for mac, windows and linux Rust Rust · 3.8k total Healthy Spotted at 501 stars
    Gained in 30 d +3.6k Score 215.2 Total 3.8k
  2. 2
    debpalash/VoiceStudio VoiceStudio is the open-source, fully-local ElevenLabs alternative — voice cloning, voice design, video dubbing, dictation, transcription & audiobook creation in 646 languages. Python Python · 98.5k total Healthy
    Gained in 30 d +46.2k Score 201.9 Total 98.5k
  3. 3
    Akshayykadam/PixelBoard Unlock Google 11's Gemini "Rambler" Natural Voice Dictation & AI Writing Tools on ANY Android phone. No root required. Java Java · 1.4k total
    Gained in 30 d +1.3k Score 128.3 Total 1.4k
  4. 4
    Nomily-Ai/nomily-app BYOK voice recording companion with ASR transcription, speaker diarization, AI summaries, and local ASR endpoint support. 1k total Mixed signals
    Gained in 30 d +983 Score 98.3 Total 1k
  5. 5
    Darlingfxx02/no-tipe-releases Free desktop dictation for macOS and Windows. Speak messages, emails and notes into your apps with local or cloud speech recognition. HTML HTML · 546 total
    Gained in 30 d +545 Score 54.5 Total 546
  6. 6
    SaarthurR/atticus-mac Fast, free voice assistant for your Mac. No API key: runs on your Claude Pro or Max plan. Sends background agents for big jobs, remembers you and learns your shortcuts. Hold ⌃⌥Space and talk. Python Python · 541 total
    Gained in 30 d +541 Score 54.1 Total 541
  7. 7
    JimLiu/baocut BaoCut: an AI video agent with an editable timeline. Transcribe, subtitle, translate, dub, cut and animate. TypeScript TypeScript · 1.6k total Mixed signals
    Gained in 30 d +1.1k Score 49.7 Total 1.6k
  8. 8
    opennookorg/betterwispr Free, open-source, local-first dictation app for macOS. Hold a shortcut, speak, and text is typed into any app. On-device speech-to-text with Whisper, Parakeet and Apple speech. Private, offline, open-source Wispr Flow alternative. Swift Swift · 497 total
    Gained in 30 d +497 Score 49.7 Total 497
  9. 9
    CerealAxis/Nola-Translator Lightweight, powerful real-time speech translation with multilingual support and a multilingual UI. TypeScript TypeScript · 322 total
    Gained in 30 d +322 Score 32.2 Total 322
  10. 10
    nyosegawa/speech.cpp Speech synthesis, speech recognition and voice activity detection for voice conversation, in C++ on ggml: Qwen3-TTS, Irodori-TTS, Qwen3-ASR, ReazonSpeech, parakeet and Silero VAD on Metal, Vulkan and the CPU, with an OpenAI-compatible server and live transcription. C++ C++ · 317 total
    Gained in 30 d +317 Score 31.7 Total 317
  11. 11
    seacen/meetcap Powerful, free, context-aware AI native meeting assistant that transcribes real-time and locally on your computer, writes the minutes, and lets your AI agent drive it. Shell Shell · 301 total
    Gained in 30 d +301 Score 30.1 Total 301
  12. 12
    niyongsheng/AudioScript [讯飞同传]免费平替——本地系统语音实时转写，国际会议、外语播客、生肉影视，屏幕浮窗、实时字幕、离线识别。Offline real‑time Language transcription, floating live subtitles. Rust Rust · 261 total
    Gained in 30 d +261 Score 26.1 Total 261
  13. 13
    raullenchai/esp32-thinks A multi-model Muse: personal AI voice assistant on ESP32 - wake word or knob, any OpenAI-compatible brain (STT/chat/TTS mix-and-match), streaming replies, out of the box. Built on muse-gadget-sdk. Shell Shell · 260 total
    Gained in 30 d +260 Score 26.0 Total 260
  14. 14
    HanyuanWang/LiveStream-Agent-Studio 面向抖音直播电商的 Windows 本地 AI Agent Studio，贯通主播发现、直播洞察、直播复盘与短视频内容编导的统一智能工作流。 Python Python · 1.8k total Mixed signals
    Gained in 30 d +782 Score 24.5 Total 1.8k
  15. 15
    cjpais/Handy A free, open source, and extensible speech-to-text application that works completely offline. Rust Rust · 37k total Healthy
    Gained in 30 d +4.3k Score 24.0 Total 37k
  16. 16
    honwee/mynah Mynah — self-hosted realtime digital human. One GPU, full admin console, Apache-2.0. 自己服务器上的实时数字人系统 Go Go · 224 total
    Gained in 30 d +224 Score 22.4 Total 224
  17. 17
    MachHongHai/HaizFlow Free Windows desktop app for AI video translation, subtitles and dubbing, with local CPU/GPU models, voice cloning, batch processing and video downloads. Python Python · 226 total Healthy
    Gained in 30 d +223 Score 22.3 Total 226
  18. 18
    andrisgauracs/whistle-esp32 Whistle speech-to-text running fully on an ESP32-S3: hold a button, say a colour in one of 7 languages, the LED does it. No network. C C · 206 total
    Gained in 30 d +206 Score 20.6 Total 206
  19. 19
    hehehai/AudioSmith Speech, voices, stories, audiobooks, dubbing and transcription, made on your Mac. Free and open source. Go Go · 193 total
    Gained in 30 d +193 Score 19.3 Total 193
  20. 20
    timoncool/speech-studio Free offline AI voice studio for Windows — text-to-speech with cloned and built-in voices, and speech recognition with speakers. Russian done right. 100% local, one native .exe, zero Python. Rust Rust · 192 total
    Gained in 30 d +192 Score 19.2 Total 192
  21. 21
    tacshi/Soundcore soundcore Work（安克 AI 录音豆 / D3200）本地管理 App：BLE 配对连接、录音管理、AI 实时转写、Wi-Fi SoftAP 批量导出 Dart Dart · 220 total Low activity
    Gained in 30 d +184 Score 18.4 Total 220
  22. 22
    AGIHunt/blurt The keyboard for the agent era: dictation, copy text from screen, translation, snaps and screen recordings for Claude Code, Codex and your other agents. Free, open source, Mac. 口喷鸡：Agent 时代的输入法。 Swift Swift · 225 total
    Gained in 30 d +184 Score 18.4 Total 225
  23. 23
    zephyr4123/speakmore SpeakMore：口述成文，划词即译。开源、免费的语音输入与翻译工具，支持 Mac 与 Windows：语音输入、语音翻译、划词翻译。兼容 Gemini、OpenAI、通义千问、DeepSeek、Kimi、智谱 GLM、MiniMax 及任意 OpenAI 兼容服务，语音输入亦可完全在本机运行。附 Typeless 逆向分析。 JavaScript JavaScript · 177 total
    Gained in 30 d +177 Score 17.7 Total 177
  24. 24
    bayshier/voicestudio-zh VoiceStudio 中文版：开源、完全本地的 ElevenLabs 替代品——语音克隆、语音设计、视频配音、听写、转写与有声书，646 种语言（译自 debpalash/VoiceStudio，AGPL-3.0） Python Python · 195 total
    Gained in 30 d +176 Score 17.6 Total 195
  25. 25
    fermionresearch/phonon Phonon: open speech recognition models (Phonon-2, Phonon-1) — CLI, CPU and CUDA images Python Python · 324 total
    Gained in 30 d +197 Score 17.5 Total 324
  26. 26
    B0yko/tern Local AI search for podcast and video archives on Apple Silicon: Whisper speech, Apple Vision OCR and SigLIP-2 visual search fused into one ranked list, with a trim editor and FCPXML export. FastAPI, vanilla JS, Tauri. Source-visible, all rights reserved. Python Python · 214 total
    Gained in 30 d +173 Score 17.3 Total 214
  27. 27
    OpenWhispr/openwhispr Voice-to-text dictation app with local (Nvidia Parakeet/Whisper) and cloud models (BYOK). Privacy-first and available cross-platform. JavaScript JavaScript · 10.5k total Healthy
    Gained in 30 d +1.6k Score 16.6 Total 10.5k
  28. 28
    yuxino/Mimi 把电脑或麦克风声音转成实时翻译字幕。Live translated subtitles from computer or microphone audio. Rust Rust · 780 total Healthy
    Gained in 30 d +326 Score 15.3 Total 780
  29. 29
    juinwei7/Shiyin Free, open-source meeting notes app for Mac: records Zoom, Meet and Teams without a bot, transcribes on-device (whisper.cpp + Breeze ASR 25), identifies speakers, and writes timestamped notes with your own Claude or ChatGPT. 拾音 C# C# · 132 total
    Gained in 30 d +132 Score 13.2 Total 132
  30. 30
    jamiepine/voicebox The open-source AI voice studio. Clone, dictate, create. Python Python · 59.2k total Mixed signals
    Gained in 30 d +3.1k Score 13.2 Total 59.2k
  31. 31
    0xShug0/audio.cpp An all-in-one, pure C++ inference engine for audio models, powered by ggml. Supports TTS, STT, VAD, voice conversion, music generation, and more, with highly optimized performance. No Python dependency. C++ C++ · 3.9k total Healthy
    Gained in 30 d +720 Score 12.7 Total 3.9k
  32. 32
    xinkyle/Voconly 本地优先 AI 语音输入工具 | Local-first AI voice typing tool. 支持 Whisper/SenseVoice/Parakeet/Qwen asr，离线可用，LLM 智能润色. Open-source speech-to-text with LLM post-processing, works offline. C++ C++ · 150 total Healthy
    Gained in 30 d +126 Score 12.6 Total 150
  33. 33
    ozcancelik/harfiyen Tarayıcıda çalışan Türkçe konuşma tanıma ve altyazı aracı. Otomatik noktalama, canlı transkript ve altyazılı video dışa aktarma. Tamamen yerel, WebGPU destekli. TypeScript TypeScript · 117 total
    Gained in 30 d +117 Score 11.7 Total 117
  34. 34
    SonicloudTech/mouse-mcp Hardware mouse MCP server for AI agents on Windows x64. USB HID control and voice dictation; requires compatible uMouse hardware and firmware. 面向 AI 智能体的硬件鼠标 MCP：USB HID 控制与语音听写，需要兼容的 uMouse 设备与固件。 TypeScript TypeScript · 114 total
    Gained in 30 d +114 Score 11.4 Total 114
  35. 35
    100yenadmin/fish-audio-hermes Official Fish Audio plugin for Hermes Agent: expressive text-to-speech, speech-to-text, voice library, cloning and voice design. Python Python · 112 total
    Gained in 30 d +112 Score 11.2 Total 112
  36. 36
    HojoAI/Hojo-ASR Hojo-ASR is a high-performance speech recognition model powered by the LLM decoder. Python Python · 473 total
    Gained in 30 d +188 Score 11.1 Total 473
  37. 37
    floatboatai/OpenMinutes OpenMinutes · 录音笔工作台：MemoTalk S1 录音的导入 · 转录 · AI 归类 · 检索复盘（Floatboat Workbench 开源实现） TypeScript TypeScript · 108 total New
    Gained in 30 d +108 Score 10.8 Total 108
  38. 38
    sapientorius/Nebulynk A self-hosted home for your team's conversations, calls, meetings, and AI-assisted follow-up. JavaScript JavaScript · 325 total Healthy
    Gained in 30 d +141 Score 10.4 Total 325
  39. 39
    alexturkey/crisperwhisper-turkce-kelime-zamani Verbatim speech-to-text with word timestamps on a 4 GB GPU: CrisperWhisper 2.0 Turbo (CT2 int8) + wav2vec2 CTC alignment. Turkish-first, Linux/WSL2. Python Python · 103 total
    Gained in 30 d +103 Score 10.3 Total 103
  40. 40
    entropyconquers/gpt-voice A small, open-source Mac dictation app that uses your ChatGPT sign-in. Speak into T3 Code, your editor, or any text field. Swift Swift · 101 total
    Gained in 30 d +101 Score 10.1 Total 101
  41. 41
    sgl-project/sglang-omni High Performance Serving Runtime For Interactive Super Intelligence System Python Python · 1.7k total Healthy
    Gained in 30 d +361 Score 10.0 Total 1.7k
  42. 42
    Osmantic/ODS ODS V3 Pre-Release: Public testing and refinement ahead of the official V3 launch. Turn your PC, Mac, or Linux box into a private AI server. Python Python · 7.7k total Healthy
    Gained in 30 d +797 Score 9.6 Total 7.7k
  43. 43
    Sorasukiawa/VoxPalm 掌声 VoxPalm：按住说话，松手出字。把遥控器和无线麦变成 Mac 的语音按钮 · Hold to talk, release to type: turn remotes and wireless mics into a voice button for your Mac Swift Swift · 96 total
    Gained in 30 d +95 Score 9.5 Total 96
  44. 44
    open-subs/opensubs Subtitle any video without uploading it. Whisper, translation, styling and burn-in — all local, in the browser, on the desktop, or from the command line. TypeScript TypeScript · 141 total
    Gained in 30 d +92 Score 9.2 Total 141
  45. 45
    KorenKrita/simul-subtitle 日语、英语视频与直播实时同传悬浮字幕（Android / macOS / Windows）｜本地离线语音识别 · 自备 LLM 翻译（BYOK） Kotlin Kotlin · 92 total
    Gained in 30 d +92 Score 9.2 Total 92
  46. 46
    recepyagmur/EnglishPractice Yerel, çevrimdışı ve taşınabilir İngilizce pratik uygulaması (Türkçe konuşanlar için): yapay zekâyla sesli/yazılı sohbet ve anında düzeltme, A1–C1 dersler ve sınavlar, Türkçe sesli öğretmen, kelime ve kalıp çalışma, YDS tarzı süreli testler. Windows ve Linux. Ollama + Gemma 4, Whisper, Kokoro, EMA… Python Python · 89 total
    Gained in 30 d +89 Score 8.9 Total 89
  47. 47
    Magerko/copilot Локальный AI-копилот для интервью и встреч (Windows, BYOK): локальная ASR, оверлей, конфиденциальность TypeScript TypeScript · 86 total New
    Gained in 30 d +86 Score 8.6 Total 86
  48. 48
    arbazsiddiqui/voxlock The best performing voice isolator there is. Keeps the caller's voice and removes the other voices in the room before speech-to-text hears them. Open source, streaming, runs on CPU and in the browser. pip install voxlock Python Python · 85 total
    Gained in 30 d +85 Score 8.5 Total 85
  49. 49
    yuezhiai/jonex All-in-One Multimodal Parsing Engine + Ontology-Powered, LLM Wiki-Driven AI-Ready Knowledge Engine Python Python · 1.6k total Mixed signals
    Gained in 30 d +300 Score 8.5 Total 1.6k
  50. 50
    veedstudio/open-edit Open-source, agent-driven editing pipeline: create subtitles, motion graphics, slides, edit and render videos. TypeScript TypeScript · 1.8k total Low activity
    Gained in 30 d +320 Score 8.4 Total 1.8k
  51. 51
    swax/dub-anything A tool that allows AI to direct the dubbing process, uses the original actor voices and does the audio generation on your local PC Python Python · 84 total
    Gained in 30 d +84 Score 8.4 Total 84
  52. 52
    techjarves/Portable-Local-Studio Portable local AI studio for Windows, Linux, and macOS. Zero-setup GUI for Image Generation, GGUF LLMs, Text to Speech & Speech to Text JavaScript JavaScript · 1.8k total Low activity
    Gained in 30 d +318 Score 8.4 Total 1.8k
  53. 53
    xixihhhh/hotclip 免费开源的 AI 剪辑 / 直播切片工具:长视频、直播回放、播客一键切成爆款竖屏短视频,直发抖音/快手/B站/小红书/视频号——AI 找高光金句、弹幕热度进爆点判断、自动加字幕、横屏转竖屏,本地运行无水印不上传 | Free open-source Opus Clip alternative, 100% local: AI clips long videos & livestream VODs into viral 9:16 shorts for TikTok & YouTube Shorts. No credits, no watermark, no uploads… TypeScript TypeScript · 412 total Healthy
    Gained in 30 d +135 Score 8.1 Total 412
  54. 54
    timoncool/dub-studio Free offline AI video dubbing studio for Windows — voice cloning, translation, subtitles & on-screen-text localization. 100% local, one native .exe, zero Python. Rust Rust · 239 total Healthy
    Gained in 30 d +96 Score 8.0 Total 239
  55. 55
    sunerpy/voltip Push-to-talk voice typing for Windows, macOS, Linux and Android. On-device or cloud speech recognition, AI polish with presets, a dictionary, rules and scenes, long recordings with subtitles; the phone works on its own or pairs end-to-end encrypted as the computer's microphone and keyboard. Rust Rust · 80 total
    Gained in 30 d +79 Score 7.9 Total 80
  56. 56
    redheadesign/music-island Music controls, local dictation, voice processing and assistant limits at the top edge of your Windows desktop. Rust Rust · 1.2k total Mixed signals
    Gained in 30 d +244 Score 7.8 Total 1.2k
  57. 57
    Animan-AI/DuckBuddy Your real-life buddy duck: an open-source embodied AI robot duck that walks, hears, sees, and has a life of its own. 让 DuckBuddy 成为你真正的生活伙伴鸭：开源具身智能小鸭机器人，运动、语音、视觉与生命层全部跑在机器人自己身上。Feetech servos + Orange Pi Zero 3W, built on Pollen Robotics' Microduck (unofficial). Rust Rust · 78 total
    Gained in 30 d +78 Score 7.8 Total 78
  58. 58
    AbhishekBarali/SpeakoFlow Free, open-source offline voice dictation for Windows, macOS, and Linux. A Wispr Flow alternative with an AI assistant that can read your screen on request and answer questions. Rust Rust · 382 total Healthy
    Gained in 30 d +125 Score 7.8 Total 382
  59. 59
    Turbo1123/Turbo-IO 雷鸟 iO / RayNeo iO 非官方 SDK：原生鸿蒙 HarmonyOS SDK/客户端、iOS 客户端及 iOS/Android 官方 App 扩展。自有模型、联网搜索、眼镜导航、录音研究、Codex 与 Web 预览，各平台能力以文档为准。面向开发者，仅供非商业学习研究；只提供源码，不提供 IPA/APK/HAP 或签名包。 Objective-C Objective-C · 320 total
    Gained in 30 d +112 Score 7.8 Total 320
  60. 60
    Forrest404/unidex Pocket e-ink OS for the Waveshare ESP32-S3 1.54" board: class timetable with calendar sync, AI voice notes for Obsidian, a Pet that meets your friends' Pets, name badges and one-button games. Install it from your browser, or join the waitlist: unidex-site.vercel.app C C · 78 total
    Gained in 30 d +77 Score 7.7 Total 78
  61. 61
    jankeesvw/omarchy-meeting-recorder Record meetings on Omarchy: mic and computer audio as two tracks, transcribed on your own machine, with speakers, chapters and a player. Rust Rust · 461 total
    Gained in 30 d +138 Score 7.7 Total 461
  62. 62
    shikki841/inaudio Offline dictation and read-aloud for the desktop. TypeScript TypeScript · 79 total
    Gained in 30 d +76 Score 7.6 Total 79
  63. 63
    altic-dev/FluidVoice Fastest and only macOS Dictation app with on-device STT and custom trained AI enhancement model. Windows, iOS testflight! Android, Linux waitlist open! A local Wispr Flow alternative. Follow https://x.com/fluidvoiceapp for more Swift Swift · 12.7k total Healthy
    Gained in 30 d +820 Score 7.5 Total 12.7k
  64. 64
    zeekk0/OpenSakura OpenSakura: MekaHime's first AI companion, open source. 3D VRoid avatar, real-time voice, emotion state, OpenRouter or Ollama brain. Python Python · 75 total
    Gained in 30 d +75 Score 7.5 Total 75
  65. 65
    FlaxXTT/Typeleast TypeLeast：按一下快捷键说话，本机识别（SenseVoice），用你自己的大模型 API Key 整理成通顺文字，直接写进光标处。macOS + Windows 11。 Swift Swift · 74 total
    Gained in 30 d +74 Score 7.4 Total 74
  66. 66
    zhuzhangxue/wechat-chat-export Windows 微信 4.1.12+ 聊天记录本地导出工具：TXT / Markdown / JSON，支持图片、文件、语音、视频、本地语音转文字和聊天预览，面向 GPT、Claude、Gemini 等 LLM。 | Local-first WeChat chat exporter for LLMs. Python Python · 116 total Healthy
    Gained in 30 d +71 Score 7.1 Total 116
  67. 67
    grigio/sonia-assistant Sonia - Local Voice Assistant in less than 13GB of RAM, TTS/STT, No Dedicated GPU required, Skills supported TypeScript TypeScript · 67 total
    Gained in 30 d +67 Score 6.7 Total 67
  68. 68
    xifan2333/fcitx5-vinput Voice input for Fcitx5 — local and cloud ASR, LLM rewriting, cross-distro packages C++ C++ · 624 total Healthy
    Gained in 30 d +144 Score 6.6 Total 624
  69. 69
    MuzeAnisichael/GreatSage GreatSage · 大贤者 — a Windows desktop voice secretary that listens, remembers across sessions, turns meetings and Markdown notes into cited minutes and todos, and asks before it acts. Cloud or local AI, auditable, with a desktop pet. Python Python · 66 total
    Gained in 30 d +65 Score 6.5 Total 66
  70. 70
    isair/jarvis Private local AI assistant for your desktop. Voice and text chat, personal memory, dictation and MCP tools. Runs offline with Ollama or OpenAI-compatible servers on macOS, Windows and Linux. Python Python · 2.2k total Mixed signals
    Gained in 30 d +281 Score 6.5 Total 2.2k
  71. 71
    equalang/equalang-skill Agent Skill for Equalang: translate PDF, DOCX, PPTX, XLSX, EPUB, subtitles, pictures, audio and video with the layout kept; transcribe recordings. For Claude Code, Codex, Cursor and more. Python Python · 61 total
    Gained in 30 d +61 Score 6.1 Total 61
  72. 72
    openai/whisper Robust Speech Recognition via Large-Scale Weak Supervision Python Python · 112k total Low activity
    Gained in 30 d +2k Score 6.1 Total 112k
  73. 73
    Zackriya-Solutions/meetily Privacy first AI meeting note taker. Download Free and open source granola, otter ai, fireflies alternative. Parakeet / Whisper live transcription, on-device speaker diarization, built on Rust. 100% local processing. Meetily (Meetly Ai - https://meetily.ai) is the #1 Self-hosted, Open-source Ai… Rust Rust · 32.4k total Mixed signals
    Gained in 30 d +1.1k Score 6.1 Total 32.4k
  74. 74
    oboroge0/hayamimi 早耳 - Real-time multilingual speech-to-text on CPU only. Live subtitles, browser dashboard, speaker labels, translation. No GPU, no cloud. Python Python · 456 total Mixed signals
    Gained in 30 d +112 Score 6.0 Total 456
  75. 75
    NVIDIA/NeMo-Speech.cpp NeMo-Speech.cpp is a lightweight C++ inference runtime for Speech models C++ C++ · 230 total Healthy
    Gained in 30 d +73 Score 5.8 Total 230
  76. 76
    donet-org-cn/FunAsrNet FunASR.NET：.NET 10 纯 C# 普通话 ASR/TTS，CPU SIMD、可选 Vulkan，浏览器和 SIP 音频示例，中文文档与真实原版测速对照。 C# C# · 57 total
    Gained in 30 d +57 Score 5.7 Total 57
  77. 77
    FluidInference/FluidAudio Frontier CoreML audio models in your apps — text-to-speech, speech-to-text, voice activity detection, and speaker diarization. In Swift, powered by SOTA open source. Swift Swift · 3.3k total Healthy
    Gained in 30 d +306 Score 5.6 Total 3.3k
  78. 78
    NOTBAD314/2ByteASR A smarter subtitle studio powered by advanced ASR models. Refine transcripts with AI and custom glossaries, build bilingual subtitles, and edit speech and video together. Python Python · 56 total Healthy
    Gained in 30 d +56 Score 5.6 Total 56
  79. 79
    oxbshw/watch-skill Give AI agents eyes, ears, and verifiable results. Watch Skill turns video, audio and screen activity into searchable, timestamped evidence and proves work with deterministic contracts, not model opinion. DeepWatch is the agent workspace built on DeepSeek Harness. Python + npm, MCP, CLI, REST, Web. Python Python · 543 total Mixed signals
    Gained in 30 d +113 Score 5.4 Total 543
  80. 80
    rasonyang/cascade-realtime-gateway Self-hosted voice gateway in Go that speaks the OpenAI Realtime (GA) WebSocket protocol and runs a cascaded ASR → LLM → TTS pipeline behind it. Keep clients unchanged while swapping speech and LLM providers at runtime Go Go · 63 total
    Gained in 30 d +54 Score 5.4 Total 63
  81. 81
    tlack/babytalk Optimized ESP32-S3/P4 fully offline speech to text and text to speech system for Micropython and AtomVM, featuring a finetuned STT model for noisy environments, plus a data generation/field capture/model finetuning framework. Includes high performance 4/8bit int kernels for Xtensa/RiscV PIE vector… C C · 54 total
    Gained in 30 d +54 Score 5.4 Total 54
  82. 82
    kuxiaowo/wechat-asr-bridge ASR bridge exposing Weixin voice input as a programmable speech transcription API on Windows Python Python · 54 total
    Gained in 30 d +54 Score 5.4 Total 54
  83. 83
    Open-Less/openless Hold a key, speak, release — AI-polished text appears at your cursor in any app. Open-source voice input for macOS & Windows. (按住快捷键说话，松开即得润色后的文字) Rust Rust · 4k total Healthy
    Gained in 30 d +327 Score 5.4 Total 4k
  84. 84
    VocaHQ/vocamac Open-source, offline voice-to-text for macOS. Hold a hotkey, speak, text appears. Private on-device dictation with multiple speech engines. Swift Swift · 161 total Healthy
    Gained in 30 d +55 Score 5.3 Total 161
  85. 85
    alexturkey/dubworld Local-first AI video dubbing pipeline: transcription, translation, speech synthesis and timing alignment. Python Python · 53 total
    Gained in 30 d +53 Score 5.3 Total 53
  86. 86
    QwenAudio/qwen-audio-agent A realtime voice runtime that keeps Agents talking, working, and present. Real-time Voice Runtime for AI Agents JavaScript JavaScript · 3.1k total Healthy
    Gained in 30 d +279 Score 5.2 Total 3.1k
  87. 87
    ishangautam7/Talvio Talk to your computer: dictation into any app, a voice assistant that answers out loud and gets things done, meeting notes, and a phone app to control your PC. Local-first, open source. Rust Rust · 52 total
    Gained in 30 d +52 Score 5.2 Total 52
  88. 88
    rafafunt/FalconSDR Wideband SDR scanner that records only real transmissions. Browser UI for local use or a headless receiver, searchable library, optional Whisper transcription. RTL-SDR and SoapySDR. Linux, Windows and macOS. Python Python · 52 total
    Gained in 30 d +52 Score 5.2 Total 52
  89. 89
    lzynb0206/WeChat-iLink-Multimodal-Bot 基于 Spring Boot、微信 iLink SDK 与阿里云百炼的多模态微信机器人，支持文本、图片、语音、Function Calling、Skill 编排和本地 RAG。 Java Java · 52 total Low activity
    Gained in 30 d +51 Score 5.1 Total 52
  90. 90
    software-mansion/runntime High-performance neural networks engine for web, built on top of TypeGPU TypeScript TypeScript · 111 total
    Gained in 30 d +51 Score 5.1 Total 111
Show more

Emerging in Speech-to-text Past weeks: Oct 26Oct 19