Upstar classe toutes les heures les projets GitHub qui montent le plus vite, dans 69 thèmes. Voir les thèmes

#speech-to-text · IA & ML

Transcription vocale

Reconnaissance vocale, transcription et dictée, des modèles ouverts aux applications locales.

Cette semaine (27 oct. – 2 nov.), en tête : hex (+3 294), VoiceStudio (+9 906) et Handy (+2 303). Les 107 projets classés ont gagné 24 223 étoiles, 12 % de plus que la semaine précédente.

Mis à jour le 2 nov., 14:38 UTC · classé toutes les heures à partir des étoiles quotidiennes de GitHub

Mis à jour il y a 2 min

Sujet GitHub ↗ (nouvel onglet)

Classement de la semaine

107 sur 107 affichés

Comment Upstar classe

  1. 1
    anomalyco/hex Local voice dictation for mac, windows and linux Rust Rust · 3,9 k au total En bonne santé Repéré à 501 étoiles
    Gagnées en 7 j +3,3 k Score 134,4 Total 3,9 k
  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 · 98,6 k au total En bonne santé
    Gagnées en 7 j +9,9 k Score 33,3 Total 98,6 k
  3. 3
    cjpais/Handy A free, open source, and extensible speech-to-text application that works completely offline. Rust Rust · 37 k au total En bonne santé
    Gagnées en 7 j +2,3 k Score 12,4 Total 37 k
  4. 4
    hehehai/AudioSmith Speech, voices, stories, audiobooks, dubbing and transcription, made on your Mac. Free and open source. Go Go · 194 au total
    Gagnées en 7 j +122 Score 12,2 Total 194
  5. 5
    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 au total Nouveau
    Gagnées en 7 j +108 Score 10,8 Total 108
  6. 6
    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 au total
    Gagnées en 7 j +104 Score 10,4 Total 114
  7. 7
    Magerko/copilot Локальный AI-копилот для интервью и встреч (Windows, BYOK): локальная ASR, оверлей, конфиденциальность TypeScript TypeScript · 86 au total Nouveau
    Gagnées en 7 j +86 Score 8,6 Total 86
  8. 8
    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 · 549 au total
    Gagnées en 7 j +161 Score 8,2 Total 549
  9. 9
    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 au total
    Gagnées en 7 j +82 Score 7,8 Total 192
  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++ · 320 au total
    Gagnées en 7 j +110 Score 7,6 Total 320
  11. 11
    Sallyn0225/eidolon-sc 和《偶像大师 闪耀色彩》偶像实时语音/文字对话的 AI 分身：日语原声 + 中文字幕、回忆原作剧情、跨角色共享记忆；支持 Google/GitHub 登录与自带密钥，Docker Compose 一键部署（参考 LAPLACE Eidolon） Python Python · 367 au total
    Gagnées en 7 j +119 Score 7,6 Total 367
  12. 12
    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 au total
    Gagnées en 7 j +61 Score 6,1 Total 96
  13. 13
    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 · 1,8 k au total Peu d’activité
    Gagnées en 7 j +217 Score 5,5 Total 1,8 k
  14. 14
    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 au total
    Gagnées en 7 j +55 Score 5,5 Total 74
  15. 15
    OpenWhispr/openwhispr Voice-to-text dictation app with local (Nvidia Parakeet/Whisper) and cloud models (BYOK). Privacy-first and available cross-platform. JavaScript JavaScript · 10,5 k au total En bonne santé
    Gagnées en 7 j +508 Score 5,1 Total 10,5 k
  16. 16
    lonthq/overtone-captions Reliable transcription, with captions cut for every screen shape from one file. An open caption format, a video.js plugin with style packs, and a CLI that recuts, burns in and exports word-timed captions. TypeScript TypeScript · 50 au total Nouveau
    Gagnées en 7 j +50 Score 5,0 Total 50
  17. 17
    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 au total
    Gagnées en 7 j +61 Score 4,8 Total 225
  18. 18
    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 · 1,8 k au total Signaux mitigés
    Gagnées en 7 j +189 Score 4,7 Total 1,8 k
  19. 19
    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 au total
    Gagnées en 7 j +55 Score 4,6 Total 195
  20. 20
    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 au total
    Gagnées en 7 j +46 Score 4,6 Total 52
  21. 21
    BoumedineBillal/esp32-pie-asr Live English speech recognition on the ESP32-P4: a 65.7M-parameter streaming transducer in 2/4-bit weights, faster than real time, on the chip alone. With six voice-control demos. C++ C++ · 48 au total
    Gagnées en 7 j +46 Score 4,6 Total 48
  22. 22
    Akshayykadam/PixelBoard Unlock Google 11's Gemini "Rambler" Natural Voice Dictation & AI Writing Tools on ANY Android phone. No root required. Java Java · 1,4 k au total
    Gagnées en 7 j +161 Score 4,6 Total 1,4 k
  23. 23
    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 au total
    Gagnées en 7 j +42 Score 4,2 Total 80
  24. 24
    olerast67/voice-teleprompter-android Suflyor (Суфлёр) — free voice-following teleprompter app for Android. Scrolls as you speak, floats over Instagram, TikTok and the camera. English and Russian speech recognized on the phone, offline, no internet permission. Телесуфлёр по голосу для Android. Kotlin Kotlin · 54 au total
    Gagnées en 7 j +41 Score 4,1 Total 54
  25. 25
    modulate-ai/speech-to-text-benchmark Reproducible speech-to-text benchmark: WER, latency and cost for Velma, Deepgram, AssemblyAI, Chirp 3, MAI-Transcribe 2, Moonshine and whisper.cpp on LibriSpeech, VoxPopuli and Common Voice. Python Python · 45 au total
    Gagnées en 7 j +40 Score 4,0 Total 45
  26. 26
    yanyan1115/ringringring 0 成本让 AI 给你打电话📞：iOS 原生通话，无需 Mac／开发者账号，无需购买或编写 App。Zero-cost AI phone calls over free SIP. Python Python · 42 au total Nouveau
    Gagnées en 7 j +40 Score 4,0 Total 42
  27. 27
    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 · 53 au total
    Gagnées en 7 j +39 Score 3,9 Total 53
  28. 28
    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 au total
    Gagnées en 7 j +39 Score 3,9 Total 103
  29. 29
    JimLiu/baocut BaoCut: an AI video agent with an editable timeline. Transcribe, subtitle, translate, dub, cut and animate. TypeScript TypeScript · 1,6 k au total Signaux mitigés
    Gagnées en 7 j +131 Score 3,4 Total 1,6 k
  30. 30
    alexturkey/dubworld Local-first AI video dubbing pipeline: transcription, translation, speech synthesis and timing alignment. Python Python · 53 au total
    Gagnées en 7 j +29 Score 2,9 Total 53
  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++ · 3,9 k au total En bonne santé
    Gagnées en 7 j +170 Score 2,8 Total 3,9 k
  32. 32
    jamiepine/voicebox The open-source AI voice studio. Clone, dictate, create. Python Python · 59,3 k au total Signaux mitigés
    Gagnées en 7 j +662 Score 2,7 Total 59,3 k
  33. 33
    CerealAxis/Nola-Translator Lightweight, powerful real-time speech translation with multilingual support and a multilingual UI. TypeScript TypeScript · 322 au total
    Gagnées en 7 j +43 Score 2,6 Total 322
  34. 34
    google-gemini/jot-gemini-transcribe-macOS Gemini 3.5 Transcribe demo. Hold a key. Speak. It types. Smart dictation for macOS. Swift Swift · 554 au total Signaux mitigés
    Gagnées en 7 j +56 Score 2,5 Total 554
  35. 35
    audioshake/audioshake-python Python client and CLI for the AudioShake API: stem separation, dialogue isolation, transcription and alignment Python Python · 24 au total
    Gagnées en 7 j +24 Score 2,4 Total 24
  36. 36
    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 au total
    Gagnées en 7 j +24 Score 2,4 Total 75
  37. 37
    Nikentaipan/rpocket-team-Telegram-Autodubsub Hệ thống tự động tải video đa nền tảng, trích xuất phụ đề (Faster-Whisper), dịch thuật AI (Gemini/OpenAI), lồng tiếng Việt (CapCut/vieNeuTTS), xóa sub gốc (PaddleOCR) và render video qua Telegram Bot. 24 au total Nouveau
    Gagnées en 7 j +24 Score 2,4 Total 24
  38. 38
    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 au total
    Gagnées en 7 j +30 Score 2,3 Total 206
  39. 39
    wassgha/rescript 🎬 Open source, transcript-based video/audio editor that lives in the browser. TypeScript TypeScript · 1 k au total Signaux mitigés
    Gagnées en 7 j +68 Score 2,2 Total 1 k
  40. 40
    NVIDIA/NeMo-Speech.cpp NeMo-Speech.cpp is a lightweight C++ inference runtime for Speech models C++ C++ · 231 au total En bonne santé
    Gagnées en 7 j +30 Score 2,1 Total 231
  41. 41
    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 au total
    Gagnées en 7 j +42 Score 2,0 Total 497
  42. 42
    fermionresearch/phonon Phonon: open speech recognition models (Phonon-2, Phonon-1) — CLI, CPU and CUDA images Python Python · 325 au total
    Gagnées en 7 j +33 Score 1,9 Total 325
  43. 43
    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 au total
    Gagnées en 7 j +29 Score 1,9 Total 261
  44. 44
    yuezhiai/jonex All-in-One Multimodal Parsing Engine + Ontology-Powered, LLM Wiki-Driven AI-Ready Knowledge Engine Python Python · 1,6 k au total Signaux mitigés
    Gagnées en 7 j +71 Score 1,8 Total 1,6 k
  45. 45
    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 au total
    Gagnées en 7 j +22 Score 1,8 Total 177
  46. 46
    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 · 413 au total En bonne santé
    Gagnées en 7 j +34 Score 1,7 Total 413
  47. 47
    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 · 12,7 k au total En bonne santé
    Gagnées en 7 j +190 Score 1,7 Total 12,7 k
  48. 48
    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 au total
    Gagnées en 7 j +29 Score 1,7 Total 320
  49. 49
    QwenAudio/qwen-audio-agent A realtime voice runtime that keeps Agents talking, working, and present. Real-time Voice Runtime for AI Agents JavaScript JavaScript · 3,1 k au total En bonne santé
    Gagnées en 7 j +81 Score 1,5 Total 3,1 k
  50. 50
    SYSTRAN/faster-whisper Faster Whisper transcription with CTranslate2 Python Python · 26,4 k au total Signaux mitigés
    Gagnées en 7 j +232 Score 1,4 Total 26,4 k
  51. 51
    openai/whisper Robust Speech Recognition via Large-Scale Weak Supervision Python Python · 112 k au total Peu d’activité
    Gagnées en 7 j +471 Score 1,4 Total 112 k
  52. 52
    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 · 783 au total En bonne santé
    Gagnées en 7 j +38 Score 1,4 Total 783
  53. 53
    EveningStudy/asmr-dubber 日语／英语／中文音视频 → 中文/英文配音与字幕。支持音色克隆、双语混音、RTF 空间处理、人声分离、批量处理和仅字幕导出。JA/EN/ZH media → Chinese/English dubbing & subtitles. Voice cloning, bilingual mixing, RTF spatial processing, vocal separation, batch processing & subtitle-only export Python Python · 278 au total En bonne santé
    Gagnées en 7 j +22 Score 1,4 Total 278
  54. 54
    k2-fsa/sherpa-onnx Speech-to-text, text-to-speech, speaker diarization, speech enhancement, source separation, and VAD using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Android, iOS, HarmonyOS, Raspberry Pi, RISC-V, RK NPU, Axera NPU, Ascend NPU, x86_64 servers, websocket… C++ C++ · 15,7 k au total En bonne santé
    Gagnées en 7 j +160 Score 1,3 Total 15,7 k
  55. 55
    sgl-project/sglang-omni High Performance Serving Runtime For Interactive Super Intelligence System Python Python · 1,7 k au total En bonne santé
    Gagnées en 7 j +46 Score 1,1 Total 1,7 k
  56. 56
    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 · 32,4 k au total Signaux mitigés
    Gagnées en 7 j +203 Score 1,1 Total 32,4 k
  57. 57
    chidiwilliams/buzz Buzz transcribes and translates audio offline on your personal computer. Powered by OpenAI's Whisper. Python Python · 22,4 k au total En bonne santé
    Gagnées en 7 j +164 Score 1,1 Total 22,4 k
  58. 58
    Muesli-HQ/muesli Muesli: agent-native local meeting transcription + dictation for macOS (Granola + WisprFlow alternative) Swift Swift · 1,5 k au total En bonne santé
    Gagnées en 7 j +39 Score 1,0 Total 1,5 k
  59. 59
    thewh1teagle/vibe Transcribe on your own! TypeScript TypeScript · 8 k au total Signaux mitigés
    Gagnées en 7 j +88 Score 1,0 Total 8 k
  60. 60
    m-bain/whisperX WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization) Python Python · 25 k au total Signaux mitigés
    Gagnées en 7 j +153 Score 1,0 Total 25 k
  61. 61
    screenpipe/screenpipe YC (S26) | Open Computer History | Continuously record your company computer work, map your workflows, help you find work worth automating, and power your agents' context Rust Rust · 22,2 k au total En bonne santé
    Gagnées en 7 j +137 Score 0,9 Total 22,2 k
  62. 62
    veedstudio/open-edit Open-source, agent-driven editing pipeline: create subtitles, motion graphics, slides, edit and render videos. TypeScript TypeScript · 1,8 k au total Peu d’activité
    Gagnées en 7 j +38 Score 0,9 Total 1,8 k
  63. 63
    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 · 4 k au total En bonne santé
    Gagnées en 7 j +56 Score 0,9 Total 4 k
  64. 64
    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 · 3,3 k au total En bonne santé
    Gagnées en 7 j +50 Score 0,9 Total 3,3 k
  65. 65
    ggml-org/whisper.cpp Port of OpenAI's Whisper model in C/C++ C++ C++ · 54,9 k au total En bonne santé
    Gagnées en 7 j +194 Score 0,8 Total 54,9 k
  66. 66
    moonshine-ai/moonshine Very low latency speech to text, intent recognition, and text to speech, for building voice agents and interfaces C++ C++ · 11,4 k au total Signaux mitigés
    Gagnées en 7 j +87 Score 0,8 Total 11,4 k
  67. 67
    nexmoe/VidBee Download video and audio from 1000+ sites, transcribe locally with speaker labels, and summarize, translate, or chat with your media using your preferred AI provider. TypeScript TypeScript · 11,1 k au total En bonne santé
    Gagnées en 7 j +84 Score 0,8 Total 11,1 k
  68. 68
    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 · 2,2 k au total Signaux mitigés
    Gagnées en 7 j +37 Score 0,8 Total 2,2 k
  69. 69
    Picovoice/porcupine On-device wake word detection powered by deep learning Python Python · 5 k au total Signaux mitigés
    Gagnées en 7 j +56 Score 0,8 Total 5 k
  70. 70
    handy-computer/transcribe.cpp ggml speech-to-text inference for 16+ model families C++ C++ · 2,1 k au total En bonne santé
    Gagnées en 7 j +36 Score 0,8 Total 2,1 k
  71. 71
    umlx5h/LLPlayer The media player for language learning, with dual subtitles, AI-generated subtitles, real-time translation, and more! C# C# · 4,5 k au total Peu d’activité
    Gagnées en 7 j +52 Score 0,8 Total 4,5 k
  72. 72
    meizhong986/WhisperJAV ASR/STT subtitle generator. Uses Qwen3-ASR, local LLM, Whisper, TEN-VAD. Noise-robust for JAV Python Python · 2,4 k au total Signaux mitigés
    Gagnées en 7 j +38 Score 0,8 Total 2,4 k
  73. 73
    moona3k/macparakeet Fast, private, local-first voice app for Apple Silicon Macs — dictation, file/media transcription, meeting recording, Transforms, and a public automation CLI. Free and open-source. Swift Swift · 755 au total Signaux mitigés
    Gagnées en 7 j +21 Score 0,8 Total 755
  74. 74
    Blaizzy/mlx-audio A text-to-speech (TTS), speech-to-text (STT) and speech-to-speech (STS) library built on Apple's MLX framework, providing efficient speech analysis on Apple Silicon. Python Python · 8,2 k au total En bonne santé
    Gagnées en 7 j +69 Score 0,8 Total 8,2 k
  75. 75
    QwenAudio/SenseVoice Open-source SenseVoiceSmall model for Mandarin, Cantonese, English, Japanese, and Korean ASR, language ID, emotion recognition, and audio event detection. C C · 9,7 k au total Signaux mitigés
    Gagnées en 7 j +75 Score 0,8 Total 9,7 k
  76. 76
    huggingface/transformers 🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training. Python Python · 168 k au total En bonne santé
    Gagnées en 7 j +305 Score 0,7 Total 168 k
  77. 77
    dograh-hq/dograh Open source voice AI platform. Self-hosted alternative to Vapi and Retell. On Prem, BYOK across Speech to Speech or LLM/STT/TTS, with a visual workflow builder, MCP native and telephony support. Python Python · 6 k au total En bonne santé
    Gagnées en 7 j +57 Score 0,7 Total 6 k
  78. 78
    off-grid-ai/OGAM The Swiss Army Knife of Offline AI. Chat, see, speak, and generate images on your phone or Mac — GGUF LLMs, vision, Whisper speech-to-text, Stable Diffusion, tool calling, and local-network servers. Runs on your CPU, GPU, or NPU. No account, no API key, zero data leaves your device. TypeScript TypeScript · 3,3 k au total Signaux mitigés
    Gagnées en 7 j +39 Score 0,7 Total 3,3 k
  79. 79
    peteonrails/voxtype Voice-to-text with push-to-talk for Wayland compositors Rust Rust · 1,7 k au total En bonne santé
    Gagnées en 7 j +28 Score 0,7 Total 1,7 k
  80. 80
    kizuna-ai-lab/sokuji Real-time two-way speech translation for bilingual meetings — auto-detects the spoken language and translates both directions, cloud or fully offline on-device. Desktop (Windows · macOS · Linux) + browser extension (Chrome · Edge) for Zoom, Meet, Teams & any app. TypeScript TypeScript · 1,5 k au total En bonne santé
    Gagnées en 7 j +25 Score 0,7 Total 1,5 k
  81. 81
    VocaHQ/vocalinux Free, open-source, 100% offline voice dictation for Linux. Speak and type anywhere via whisper.cpp, Whisper & VOSK engines, GPU-accelerated, works on X11 + Wayland! Python Python · 984 au total En bonne santé
    Gagnées en 7 j +20 Score 0,6 Total 984
  82. 82
    huggingface/speech-to-speech Build voice agents with open-source models Python Python · 13,6 k au total En bonne santé
    Gagnées en 7 j +73 Score 0,6 Total 13,6 k
  83. 83
    OpenMOSS/MOSS-Transcribe-Diarize A 0.9B model for long-form transcription in 50+ languages with speaker diarization, timestamps, and acoustic event awareness Python Python · 2,2 k au total Peu d’activité
    Gagnées en 7 j +29 Score 0,6 Total 2,2 k
  84. 84
    khoj-ai/khoj Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into your personal, autonomous AI (gpt, claude, gemini, llama, qwen, mistral). Get started - free. Python Python · 37,9 k au total Peu d’activité
    Gagnées en 7 j +118 Score 0,6 Total 37,9 k
  85. 85
    tmoroney/auto-subs On-device subtitle generation that connects directly to DaVinci Resolve, Premiere, and After Effects. TypeScript TypeScript · 4,5 k au total En bonne santé
    Gagnées en 7 j +40 Score 0,6 Total 4,5 k
  86. 86
    microsoft/VibeVoice Open-Source Frontier Voice AI Python Python · 55,1 k au total Signaux mitigés
    Gagnées en 7 j +138 Score 0,6 Total 55,1 k
  87. 87
    jianchang512/pyvideotrans Translate the video from one language to another and embed dubbing & subtitles. Python Python · 19,6 k au total En bonne santé
    Gagnées en 7 j +81 Score 0,6 Total 19,6 k
  88. 88
    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 · 7,7 k au total En bonne santé
    Gagnées en 7 j +48 Score 0,5 Total 7,7 k
  89. 89
    spotify/basic-pitch A lightweight yet powerful audio-to-MIDI converter with pitch bend detection Python Python · 6 k au total Peu d’activité
    Gagnées en 7 j +42 Score 0,5 Total 6 k
  90. 90
    akdeb/ElatoAI Realtime Voice AI with 100+ Models on Arduino ESP32 with Secure Websockets and Edge Functions for AI Companions, and Devices TypeScript TypeScript · 2,1 k au total Signaux mitigés
    Gagnées en 7 j +24 Score 0,5 Total 2,1 k
  91. 91
    zackees/transcribe-anything Multi-backend whisper app. Blazing fast. Mac-arm optimized. Easy install. Input a local file or url and this service will transcribe it using Whisper AI. Completely private and Free 🤯🤯🤯 Python Python · 1,5 k au total Peu d’activité
    Gagnées en 7 j +20 Score 0,5 Total 1,5 k
  92. 92
    liuzhao1225/YouDub-webui Open-source AI video localization and dubbing for YouTube/Bilibili: speech recognition, subtitle translation, voice cloning, audio mixing and rendering. 开源 AI 视频翻译配音工具。 TypeScript TypeScript · 5,8 k au total En bonne santé
    Gagnées en 7 j +39 Score 0,5 Total 5,8 k
  93. 93
    BasedHardware/omi AI that sees your screen, listens to your conversations and tells you what to do Python Python · 13,9 k au total En bonne santé
    Gagnées en 7 j +56 Score 0,5 Total 13,9 k
  94. 94
    Vexa-ai/vexa Open-source meeting transcription API for Google Meet, Microsoft Teams & Zoom. Auto-join bots, real-time WebSocket transcripts, MCP server for AI agents. Self-host or use hosted SaaS. Python Python · 2,9 k au total En bonne santé
    Gagnées en 7 j +25 Score 0,5 Total 2,9 k
  95. 95
    NVIDIA-NeMo/Speech A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech) Python Python · 18,7 k au total En bonne santé
    Gagnées en 7 j +63 Score 0,5 Total 18,7 k
  96. 96
    niedev/RTranslator Open source real-time translation app for Android that runs locally Java Java · 10,6 k au total Signaux mitigés
    Gagnées en 7 j +44 Score 0,4 Total 10,6 k
  97. 97
    jdepoix/youtube-transcript-api This is a python API which allows you to get the transcript/subtitles for a given YouTube video. It also works for automatically generated subtitles and it does not require an API key nor a headless browser, like other selenium based solutions do! Python Python · 8,5 k au total Peu d’activité
    Gagnées en 7 j +39 Score 0,4 Total 8,5 k
  98. 98
    pyannote/pyannote-audio Neural building blocks for speaker diarization: speech activity detection, speaker change detection, overlapped speech detection, speaker embedding Jupyter Notebook Jupyter Notebook · 10,8 k au total Peu d’activité
    Gagnées en 7 j +42 Score 0,4 Total 10,8 k
  99. 99
    mozilla-ai/llamafile Distribute and run LLMs with a single file. C++ C++ · 26,5 k au total Signaux mitigés
    Gagnées en 7 j +63 Score 0,4 Total 26,5 k
  100. 100
    openvinotoolkit/openvino OpenVINO™ is an open source toolkit for optimizing and deploying AI inference C++ C++ · 11,1 k au total En bonne santé
    Gagnées en 7 j +39 Score 0,4 Total 11,1 k
  101. 101
    modelscope/FunClip FunASR-powered video transcription, subtitle generation, and LLM-assisted clipping tool with a local Gradio UI. Python Python · 6,5 k au total En bonne santé
    Gagnées en 7 j +29 Score 0,4 Total 6,5 k
  102. 102
    abus-aikorea/voice-pro Gradio WebUI for creators and developers, featuring key TTS (Edge-TTS, kokoro) and zero-shot Voice Cloning (E2 & F5-TTS, CosyVoice), with Whisper audio processing, YouTube download, Demucs vocal isolation, and multilingual translation. Python Python · 13,4 k au total Peu d’activité
    Gagnées en 7 j +29 Score 0,3 Total 13,4 k
  103. 103
    argmaxinc/argmax-oss-swift On-device Speech AI for Apple Silicon Swift Swift · 6,4 k au total Signaux mitigés
    Gagnées en 7 j +20 Score 0,2 Total 6,4 k
  104. 104
    QuentinFuxa/WhisperLiveKit Real-time, local speech-to-text with streaming ASR, speaker diarization, translation, and OpenAI/Deepgram-compatible APIs. Python Python · 11,2 k au total En bonne santé
    Gagnées en 7 j +26 Score 0,2 Total 11,2 k
  105. 105
    KoljaB/RealtimeSTT A robust, efficient, low-latency speech-to-text library with advanced voice activity detection, wake word activation and instant transcription. Python Python · 10,2 k au total En bonne santé
    Gagnées en 7 j +21 Score 0,2 Total 10,2 k
  106. 106
    leon-ai/leon 🧠 Leon is your open-source personal assistant. TypeScript TypeScript · 17,6 k au total Signaux mitigés
    Gagnées en 7 j +25 Score 0,2 Total 17,6 k
  107. 107
    alphacep/vosk-api Offline speech recognition API for Android, iOS, Raspberry Pi and servers with Python, Java, C# and Node Jupyter Notebook Jupyter Notebook · 15,2 k au total Peu d’activité
    Gagnées en 7 j +23 Score 0,2 Total 15,2 k

Émergents en Transcription vocale Semaines passées : 26 oct.19 oct.