Categories
Speech AI.
Local speech-to-text and text-to-speech. Transcription, dictation, and voice synthesis you can run on your machine.
- Rank 1. whisper.cppC/C++ port of Whisper for fast local transcription.MIT · Linux, macOS, +1GitHub stars: 53.6k
- Rank 2. GPT-SoVITSFew-shot voice cloning and cross-lingual TTS with a full training WebUI.MIT · Linux, macOS, +1GitHub stars: 61.7k
- Rank 3. Faster-WhisperWhisper reimplementation on CTranslate2 for faster local ASR.MIT · Linux, macOS, +1GitHub stars: 25.4k
- Rank 4. WhisperOpenAI’s speech-to-text model you can run locally.MIT · Linux, macOS, +1GitHub stars: 108.9k
- Rank 5. whisperXWhisper with word-level timestamps and speaker diarization for real subtitles.Other · Linux, macOS, +1GitHub stars: 24k
- Rank 6. PiperFast local neural text-to-speech that runs on CPU.MIT · Linux, macOS, +1GitHub stars: 11.3k
- Rank 7. F5-TTSMIT flow-matching TTS with expressive multilingual voices at consumer-GPU speed.MIT · Linux, macOS, +1GitHub stars: 15.2k
- Rank 8. CSMSesame’s 1B conversational speech model behind the viral Maya voice demo.Apache 2.0 · Linux, macOS, +1GitHub stars: 14.7k
- Rank 9. kokoro-onnxKokoro 82M voices as ONNX — real-time TTS on CPU with zero GPU.MIT · Linux, macOS, +1GitHub stars: 2.7k
