#text-to-speech · IA & ML
Synthèse vocale
Synthèse vocale et clonage de voix, des modèles ouverts aux moteurs et aux applications qui les font tourner.
Cette semaine (27 oct. – 2 nov.), en tête : VoiceStudio (+9 734), IP-Bot (+199) et chanh-dien-online (+159). Les 88 projets classés ont gagné 22 220 étoiles, 14 % de moins que la semaine précédente.
Mis à jour le 2 nov., 17:37 UTC · classé toutes les heures à partir des étoiles quotidiennes de GitHub
Mis à jour il y a 10 min
Classement de la semaine
Classement complet, avec les dépôts masqués par défaut. Revenir au classement
- 1debpalash/VoiceStudio VoiceStudio is the open-source, fully-local ElevenLabs alternative — voice cloning, voice design, video dubbing, dictation, transcription & audiobook creation in 646 languages.Gagnées en 7 j +9,7 k Score 32,6 Total 98,8 k
- 2pyqdcyy123-byte/IP-Bot IP Bot 免费开源的数字人IP口播智能体视频创作工作台及后台。罗根旗博士直播间同款。可本地/云端部署。Gagnées en 7 j +199 Score 19,9 Total 199
- 3kentjuno/chanh-dien-online Chánh điện online 2.5D + bộ overlay TikTok LIVE (Node, Edge TTS). MIT.Gagnées en 7 j +159 Score 15,9 Total 159
- 4breezeblue-ai/breeze-tts Official PyTorch inference for Breeze TTS 2Gagnées en 7 j +400 Score 13,0 Total 1,3 k
- 5hehehai/AudioSmith Speech, voices, stories, audiobooks, dubbing and transcription, made on your Mac. Free and open source.Gagnées en 7 j +118 Score 11,8 Total 194
- 6C4rohan/Lampline Build AI phone agents on your own computer and test every change with an AI caller. Open source, runs free with no API keys, cents per call with your own keys. Imports Dialogflow CX.Gagnées en 7 j +200 Score 11,0 Total 530
- 7Esmerubphire/astrbot_plugin_feiyu_voice AstrBot plugin and local HTTP service for Feiyu TTS, RVC v1 and optional score singingGagnées en 7 j +86 Score 8,6 Total 130
- 8HamSanders/soundbox Free, open-source, local alternative to ElevenLabs and Suno. AI sound effects, music with lyrics, text-to-speech and voice cloning on your own GPU (Stable Audio, ACE-Step and more). No account, no credits, offline. Windows/macOS app, HTTP API and a 21-tool MCP server for Claude Code and Cursor.Gagnées en 7 j +85 Score 8,5 Total 130
- 9inclusionAI/Ming-3.0-tts Ming-3.0-tts is an open-source TTS model family with 0.5B dense and 7.9B-A1.3B MoE variants, supporting multilingual speech, voice cloning, voice design, and natural-language control.Gagnées en 7 j +148 Score 8,4 Total 461
- 10Edge0-AI/Audio8_TTS SOTA-Class TTS at Compact ScaleGagnées en 7 j +360 Score 8,2 Total 2,3 k
- 11HoppouAI/Breeze-TTS-2.cpp Bilingual English and Mandarin text to speech in C++ and GGUF. Voice design, cloning, direction and experimental voice conversion. Vulkan backend, streaming HTTP and WebSocket server, web UI and a C API.Gagnées en 7 j +81 Score 8,1 Total 142
- 12Sallyn0225/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)Gagnées en 7 j +123 Score 7,8 Total 373
- 13timoncool/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.Gagnées en 7 j +82 Score 7,7 Total 194
- 14nyosegawa/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.Gagnées en 7 j +109 Score 7,5 Total 320
- 15Yuuyuko-uu/dsh-tts-bridge DSH 朗读桥:会话里的话自动交给 DeepSeek 网页端朗读,声音从你自己的电脑里出来Gagnées en 7 j +81 Score 7,0 Total 216
- 16alexturkey/voxcpm2-turkce-ses-tasarimi Turkish voice design with VoxCPM2 on a 4 GB GPU: describe a voice, pick a variant, read text in 30 languages. Patched audio.cpp, local UI in 30 languages, 14 ready-made voices.Gagnées en 7 j +113 Score 6,9 Total 378
- 17haiderfarooq3/paper-reel Claude Code skill: faceless 9:16 explainer reels in a cut-paper style. Voice-timed scenes, word-by-word captions. Free, local, no API keys.Gagnées en 7 j +67 Score 6,7 Total 78
- 18sahilmahendrakar/paradee An 8M-parameter English text-to-speech model distilled from Kokoro-82M. 9 MB, runs 18x real time on one CPU thread.Gagnées en 7 j +73 Score 6,7 Total 192
- 19dramaclaw/dramaclaw A general-purpose AIGC video engine: script to finished film in one pipeline — dramas, ads, product videos, otome games, and more. | 通用 AIGC 视频引擎 —— 从剧本到成片一条流水线,漫剧、广告、电商、乙游皆可Gagnées en 7 j +495 Score 6,2 Total 7 k
- 20assafkip/claudemy Claudemy: an open-source alternative to Udemy and Coursera. Give Claude a topic, it researches the web and builds a course of 2-minute audio lessons with cited sources. A free Claude Code skill.Gagnées en 7 j +129 Score 6,0 Total 591
- 21techjarves/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 TextGagnées en 7 j +234 Score 5,9 Total 1,8 k
- 22beiyege-01/dsh-voice-ai-girlfriend 语音 AI 女友(Voice AI girlfriend for DeepSeek Harness):Whisper 语音输入 + Qwen3-TTS 声音克隆 + 句子级流式朗读 + 数字人动画窗。插话/排队双模式,说话即打断。Gagnées en 7 j +156 Score 5,8 Total 888
- 23harry0703/MoneyPrinterTurbo 利用 AI 大模型和自动化工作流,根据主题或关键词一键生成高清短视频。Generate HD short videos from a topic or keyword with an automated AI workflow.Gagnées en 7 j +2 k Score 5,5 Total 137 k
- 24dongtaowei54-sys/root-word-animation 英语词根记忆短视频生成器:一条线 + 一颗球,把词根演成 9:16 记忆短片(design table → SVG 动画 → edge-tts → 逐帧渲染 → 五道校验)Gagnées en 7 j +49 Score 4,9 Total 49
- 25gradium-ai/xn-ptts Phonon TTS inference using xnGagnées en 7 j +87 Score 4,8 Total 412
- 26ddalcu/mlx-serve Native LLM inference server for Apple Silicon. OpenAI + Anthropic API compatible. No Python. Zig backend, Swift frontend macOS app with chat, music, voice, video generation.Gagnées en 7 j +221 Score 4,8 Total 2,3 k
- 27bayshier/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)Gagnées en 7 j +55 Score 4,6 Total 197
- 28ishangautam7/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.Gagnées en 7 j +45 Score 4,5 Total 52
- 29Vincentwei1021/anything2explainer Topic in, narrated explainer video out. A Claude Code / Codex skill that turns any topic into a black-canvas motion-graphics explainer video with TTS voiceover, subtitles and a chapter progress bar. Chinese or English; every frame drawn in code with Remotion.Gagnées en 7 j +226 Score 4,3 Total 3 k
- 30RVC-Boss/GPT-SoVITS 1 min voice data can also be used to train a good TTS model! (few shot voice cloning)Gagnées en 7 j +783 Score 3,1 Total 64,6 k
- 31leemysw/yovoice Open-source local AI audio & music studio for macOS & Windows. TTS, voice cloning, songs with lyrics, and multi-track scores — 100% offline, zero API fees.Gagnées en 7 j +131 Score 3,0 Total 2 k
- 32alexturkey/dubworld Local-first AI video dubbing pipeline: transcription, translation, speech synthesis and timing alignment.Gagnées en 7 j +29 Score 2,9 Total 53
- 330xShug0/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.Gagnées en 7 j +166 Score 2,7 Total 3,9 k
- 34jamiepine/voicebox The open-source AI voice studio. Clone, dictate, create.Gagnées en 7 j +647 Score 2,7 Total 59,3 k
- 35aashish254/Aniflow 🎬 Autonomous AI Studio for Manhwa & Webtoon Recaps — Vision Pipeline (YOLOv8 + Magi v2), Multi-Voice TTS & Video SynthesisGagnées en 7 j +25 Score 2,5 Total 67
- 36Nikentaipan/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.Gagnées en 7 j +24 Score 2,4 Total 24
- 37zeekk0/OpenSakura OpenSakura: MekaHime's first AI companion, open source. 3D VRoid avatar, real-time voice, emotion state, OpenRouter or Ollama brain.Gagnées en 7 j +23 Score 2,3 Total 75
- 38k2-fsa/OmniVoice High-Quality Voice Cloning TTS for 600+ LanguagesGagnées en 7 j +289 Score 2,3 Total 16,2 k
- 39wj-sidiss/otopilot Turn a topic into a finished YouTube Short/video: script, free & CC0 images, voice-over, subtitles, thumbnail. Runs locally, no key needed. Use with Claude Code / Codex. 15-language UI. MITGagnées en 7 j +28 Score 2,3 Total 181
- 40Alisa0808/vox-director Turn one topic into a finished Vox-style paper-collage explainer/ad video — automated end to end on Atlas Cloud + ffmpeg. An agent skill.Gagnées en 7 j +110 Score 2,2 Total 2,6 k
- 41Saganaki22/ComfyUI-Breeze-TTS-2 Breeze TTS 2 nodes for ComfyUI: voice clone, voice design, and voice direction with bilingual (EN/ZH) speech, inline vocal events, INT8 ConvRot quantized builds, and full ComfyUI / AIMDO dynamic-VRAM integration.Gagnées en 7 j +24 Score 2,2 Total 143
- 42Hiruynk/AnifLive-TTS A low-latency, high-quality multilingual voice-cloning TTS runtimeGagnées en 7 j +22 Score 2,2 Total 36
- 43NVIDIA/NeMo-Speech.cpp NeMo-Speech.cpp is a lightweight C++ inference runtime for Speech modelsGagnées en 7 j +30 Score 2,1 Total 231
- 44KittenML/KittenTTS Open-source State-of-the-art TTS model which runs on a CPU 😻Gagnées en 7 j +271 Score 2,1 Total 16,8 k
- 45ciddwd/overlay-translator 无需 ROOT 的开源 Android 屏幕实时翻译工具,适合游戏、视觉小说和漫画。支持端侧与云端 OCR、离线 LLM、多种翻译服务和文字朗读(TTS),译文可直接显示在画面上。Open-source no-root Android real-time screen translator for games, visual novels, and manga. Supports on-device and cloud OCR, offline LLMs, multiple translation services, on-screen translations, and…Gagnées en 7 j +69 Score 2,1 Total 1,2 k
- 46hexgrad/kokoro https://hf.co/hexgrad/Kokoro-82MGagnées en 7 j +177 Score 1,8 Total 9,9 k
- 47pnnbao97/VieNeu-TTS Vietnamese TTS with instant voice cloning • On-device • Real-time CPU inference • 48kHz audio quality • Chuyển văn bản thành giọng nói tiếng Việt • Text to speech tiếng Việt • TTS tiếng ViệtGagnées en 7 j +93 Score 1,7 Total 3,1 k
- 48OpenBMB/VoxCPM VoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life CloningGagnées en 7 j +325 Score 1,6 Total 41 k
- 49QwenAudio/qwen-audio-agent A realtime voice runtime that keeps Agents talking, working, and present. Real-time Voice Runtime for AI AgentsGagnées en 7 j +81 Score 1,5 Total 3,1 k
- 50readest/readest Readest is a modern, feature-rich ebook reader designed for avid readers offering seamless cross-platform access, powerful tools, and an intuitive interface to elevate your reading experience.Gagnées en 7 j +233 Score 1,5 Total 25,9 k
- 51resemble-ai/chatterbox SoTA open-source TTSGagnées en 7 j +230 Score 1,4 Total 27,5 k
- 52EveningStudy/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 exportGagnées en 7 j +22 Score 1,4 Total 278
- 53k2-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…Gagnées en 7 j +163 Score 1,3 Total 15,7 k
- 54OHF-Voice/piper1-gpl Fast and local neural text-to-speech engineGagnées en 7 j +98 Score 1,3 Total 6,1 k
- 55QwenLM/Qwen3-TTS Qwen3-TTS is an open-source series of TTS models developed by the Qwen team at Alibaba Cloud, supporting stable, expressive, and streaming speech generation, free-form voice design, and vivid voice cloning.Gagnées en 7 j +147 Score 1,2 Total 14,2 k
- 56sgl-project/sglang-omni High Performance Serving Runtime For Interactive Super Intelligence SystemGagnées en 7 j +46 Score 1,1 Total 1,7 k
- 57MartinDelophy/ai-video-editor Open-source, local-first video editor where creators and AI agents edit the same real timeline.Gagnées en 7 j +31 Score 1,0 Total 931
- 58index-tts/index-tts An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech SystemGagnées en 7 j +153 Score 1,0 Total 24,9 k
- 59kyutai-labs/pocket-tts A TTS that fits in your CPU (and pocket)Gagnées en 7 j +89 Score 0,9 Total 10,2 k
- 60FluidInference/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.Gagnées en 7 j +49 Score 0,9 Total 3,3 k
- 61Aratako/Irodori-TTS A Flow Matching-based Text-to-Speech Model with Emoji-driven Style ControlGagnées en 7 j +31 Score 0,8 Total 1,5 k
- 62moonshine-ai/moonshine Very low latency speech to text, intent recognition, and text to speech, for building voice agents and interfacesGagnées en 7 j +85 Score 0,8 Total 11,4 k
- 63fishaudio/fish-speech SOTA Open Source TTSGagnées en 7 j +146 Score 0,8 Total 33,5 k
- 64Huanshere/VideoLingo Netflix-level subtitle cutting, translation, alignment, and even dubbing - one-click fully automated AI video subtitle team | Netflix级字幕切割、翻译、对齐、甚至加上配音,一键全自动视频搬运AI字幕组Gagnées en 7 j +106 Score 0,8 Total 19 k
- 65mudler/LocalAI LocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.Gagnées en 7 j +171 Score 0,8 Total 50,1 k
- 66Blaizzy/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.Gagnées en 7 j +67 Score 0,7 Total 8,2 k
- 67QwenAudio/CosyVoice Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.Gagnées en 7 j +114 Score 0,7 Total 24,2 k
- 68OpenMOSS/MOSS-TTS-Nano A 100M-parameter multilingual TTS model for real-time CPU inference, voice cloning, and 48 kHz stereo generationGagnées en 7 j +49 Score 0,7 Total 4,6 k
- 69IAHispano/Applio A simple, high-quality voice conversion tool focused on ease of use and performance.Gagnées en 7 j +44 Score 0,7 Total 3,9 k
- 70huggingface/speech-to-speech Build voice agents with open-source modelsGagnées en 7 j +74 Score 0,6 Total 13,6 k
- 71kizuna-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.Gagnées en 7 j +24 Score 0,6 Total 1,5 k
- 72microsoft/VibeVoice Open-Source Frontier Voice AIGagnées en 7 j +136 Score 0,6 Total 55,1 k
- 73jianchang512/pyvideotrans Translate the video from one language to another and embed dubbing & subtitles.Gagnées en 7 j +80 Score 0,6 Total 19,6 k
- 74Tencent-Hunyuan/AuK AuK: An Open-Source Foundational Model for Speech Generation and EditingGagnées en 7 j +22 Score 0,6 Total 1,6 k
- 75met4citizen/TalkingHead Talking Head (3D): A JavaScript class for real-time lip-sync using full-body 3D avatars.Gagnées en 7 j +20 Score 0,5 Total 1,7 k
- 76openutau/OpenUtau Open singing synthesis platform / Open source UTAU successorGagnées en 7 j +33 Score 0,5 Total 4,5 k
- 77rany2/edge-tts Use Microsoft Edge's online text-to-speech service from Python WITHOUT needing Microsoft EdgeGagnées en 7 j +54 Score 0,5 Total 12,4 k
- 78remsky/Kokoro-FastAPI Dockerized OpenAI-compatible wrapper for Kokoro-82M text-to-speech w/multiplatform CPU, AMD, NVIDIA GPU PyTorch; multi-speaker, clone-tuning, caption timestamps, SSML, optional readalong web UIGagnées en 7 j +35 Score 0,5 Total 5,6 k
- 79NVIDIA-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)Gagnées en 7 j +62 Score 0,5 Total 18,7 k
- 80DrewThomasson/ebook2audiobook Generate audiobooks from e-books, 50+ TTS engines with voice cloning and 1696 languages!Gagnées en 7 j +64 Score 0,4 Total 20,5 k
- 81SWivid/F5-TTS Official code for "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"Gagnées en 7 j +46 Score 0,4 Total 15,5 k
- 82denizsafak/abogen Generate audiobooks from EPUBs, PDFs and text with synchronized captions.Gagnées en 7 j +26 Score 0,3 Total 6,2 k
- 83myshell-ai/OpenVoice Instant voice cloning by MIT and MyShell. Audio foundation model.Gagnées en 7 j +60 Score 0,3 Total 38,1 k
- 84espeak-ng/espeak-ng eSpeak NG is an open source speech synthesizer that supports more than hundred languages and accents.Gagnées en 7 j +20 Score 0,2 Total 7 k
- 85abus-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.Gagnées en 7 j +27 Score 0,2 Total 13,4 k
- 86santinic/audiblez Generate audiobooks from e-booksGagnées en 7 j +21 Score 0,2 Total 8,8 k
- 87leon-ai/leon 🧠 Leon is your open-source personal assistant.Gagnées en 7 j +24 Score 0,2 Total 17,6 k
- 882noise/ChatTTS A generative speech model for daily dialogue.Gagnées en 7 j +31 Score 0,2 Total 40 k
Émergents en Synthèse vocale Semaines passées : 26 oct.19 oct.