speech processing / AI dubbing
Voice-Pro is a Gradio WebUI for creators and developers that combines speech recognition (Whisper), text-to-speech (Edge-TTS, kokoro), zero-shot voice cloning (E2/F5-TTS, CosyVoice), translation, YouTube downloading, Demucs vocal isolation, and dubbing into one tool.
Same problem, same approach. Swapping one for another is a config change, not a rewrite.
Choose for Apache-2.0 licensed video dubbing pipeline with audio mixing and rendering, and strong YouTube/Bilibili support.
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。
Choose for a Gradio UI focused on audiobook generation from PDF/EPUB and video dubbing, possibly simpler than Voice-Pro.
Turn PDFs and EPUBs into audiobooks; subtitles or videos into dubbed videos (including translation), and more. For free. Pandrator uses local models, including voice-cloning (instant, RVC-enhanced, XTTS fine-tuning) and LLM processing. It aspires to be a user-friendly app with a GUI, an installer and all-in-one packages.
Choose as a fully-local ElevenLabs alternative with voice design, video dubbing, and 646-language coverage; actively developed.
VoiceStudio is the open-source, fully-local ElevenLabs alternative — voice cloning, voice design, video dubbing, dictation, transcription & audiobook creation in 646 languages.
Choose for a Go-based full video translation/dubbing pipeline with LLM integration, optimized for YouTube, possibly faster to run.
AI video translation & dubbing tool for humans and AI Agents, powered by LLMs. Full pipeline: download, transcribe, translate, TTS dub, reformat, cover generation. 100+ languages, optimized for YouTube, TikTok, Bilibili, Douyin, and more.AI视频翻译配音工具，面向人类与AI Agent，100+语言全链路，CLI分阶段调用，适配抖音、小红书、哔哩哔哩、视频号、TikTok、YouTube
Solves the same problem with a different architecture or at a different layer. Expect to rewrite the integration.
Choose when you need few-shot voice cloning with as little as 1 minute of data, as a standalone model/toolkit rather than a full webui.
1 min voice data can also be used to train a good TTS model! (few shot voice cloning)
Choose for high-quality voice cloning TTS covering 600+ languages as a standalone model, not a full webui.
High-Quality Voice Cloning TTS for 600+ Languages
Choose for tokenizer-free multilingual TTS with creative voice design and cloning, as a model-level alternative.
VoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning
Choose if you want an OpenAI-compatible STT API server (faster-whisper) instead of a webui.
Choose as a full speech toolkit (ASR, TTS, etc.) to build custom pipelines programmatically instead of using a ready webui.
Easy-to-use Speech Toolkit including Self-Supervised Learning model, SOTA/Streaming ASR with punctuation, Streaming TTS with text frontend, Speaker Verification System, End-to-End Speech Translation and Keyword Spotting. Won NAACL2022 Best Demo Award.
Choose for a research all-in-one simultaneous speech recognition/translation/synthesis model if you need an experimental end-to-end solution.
StreamSpeech is an “All in One” seamless model for offline and simultaneous speech recognition, speech translation and speech synthesis.
An earlier or more limited way to do the job. Still the right call when you need something small, proven, or CPU-only.
Choose for a lightweight real-time Whisper subtitle/translation pop-up if you only need streaming display.
The subtitles and translations are generated in real-time and displayed as pop-ups.
Choose for a simple Whisper subtitle WebUI if transcription/subtitles are all you need.
A Web UI for easy subtitle using whisper model.
Choose for a minimal scripted auto-transcription CLI without a UI.
Auto transcribe tool based on whisper
Choose for a lightweight local webui for transcription/translation/subtitle editing if you don't need TTS or dubbing.
Transcribe any audio to text, translate and edit subtitles 100% locally with a web UI. Powered by whisper models!
Choose for a Whisper-based subtitle generation tool (Web-UI + CLI + Python package) if you only need subtitles.
🎞️ Subtitles generation tool (Web-UI + CLI + Python package) powered by OpenAI's Whisper and its variants 🎞️
Choose for converting e-books to audiobooks with voice cloning and many languages; specialized for books.
Generate audiobooks from e-books, voice cloning & 1158+ languages!
Choose for realtime streaming transcription/translation of long audio as a library/script.
Whisper realtime streaming for long speech-to-text transcription and translation
Choose for a TTS-focused Gradio WebUI/API around multiple TTS models if you don't need STT/dubbing.
🍦 Speech-AI-Forge is a project developed around TTS generation model, implementing an API Server and a Gradio-based WebUI.
An older archived zero-shot TTS model; pick only if you specifically need that implementation.
An open source implementation of Microsoft's VALL-E X zero-shot TTS model. Demo is available in https://plachtaa.github.io/vallex/
Choose for a Gradio/React WebUI unifying many TTS models if you primarily need voice generation, not STT or dubbing.
A single Gradio + React WebUI with extensions for ACE-Step, OmniVoice, Kimi Audio, Piper TTS, GPT-SoVITS, CosyVoice, XTTSv2, DIA, Kokoro, OpenVoice, ParlerTTS, Stable Audio, MMS, StyleTTS2, MAGNet, AudioGen, MusicGen, Tortoise, RVC, Vocos, Demucs, SeamlessM4T, and Bark!
Does the same job, but ships as an app. Useful to a person, not swappable into a codebase.
Choose if you want a native Linux offline note-taking app with STT/TTS/translation, not a webui.
Speech Note Linux app. Note taking, reading and translating with offline Speech to Text, Text to Speech and Machine translation.
Choose if you prefer a cross-platform desktop app for batch subtitles, translation, dubbing, and burning rather than a webui.
视频转字幕、字幕翻译、AI 配音与声音克隆、字幕烧录——免费开源的一站式桌面工具。基于 Whisper / FunASR 等本地模型离线语音转文字，批量处理 + 全平台 GPU 加速，跨 Windows / macOS / Linux。Free, open-source desktop app to generate, translate, dub & burn video subtitles — local Whisper speech-to-text, AI dubbing & voice cloning, offline, GPU-accelerated.
These projects were analysed and named voice-pro among their alternatives. The relationship is not symmetric — how voice-pro rates them is a separate judgement, made when voice-pro is analysed in its own right.
calls voice-pro “Choose for a ready-made Gradio app aggregating TTS/cloning tools, not a library you embed.”
VoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning
calls voice-pro “A Gradio WebUI that wraps multiple TTS/voice-cloning engines including CosyVoice; choose for GUI experimentation, not code integration.”
Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.
calls voice-pro “For an end-user graphical UI combining multiple TTS and voice cloning engines, rather than a library.”
Lightning-Fast, On-Device, Multilingual TTS — running natively via ONNX.
calls voice-pro “Choose it when you want a Gradio WebUI for experimenting with TTS and voice cloning models.”
VoiceStudio is the open-source, fully-local ElevenLabs alternative — voice cloning, voice design, video dubbing, dictation, transcription & audiobook creation in 646 languages.