Skip to content
Fossfits
Alternatives

ElevenLabs.

Local text-to-speech when a hosted voice API is the wrong fit.

5 listedCatalog Sep 1, 2026

  1. Rank 1. PiperFast local neural text-to-speech that runs on CPU.GitHub stars: 11k
  2. Rank 2. kokoro-onnxKokoro 82M voices as ONNX — real-time TTS on CPU with zero GPU.GitHub stars: 2.7k
  3. Rank 3. GPT-SoVITSFew-shot voice cloning and cross-lingual TTS with a full training WebUI.GitHub stars: 62k
  4. Rank 4. CSMSesame’s 1B conversational speech model behind the viral Maya voice demo.GitHub stars: 15k
  5. Rank 5. F5-TTSMIT flow-matching TTS with expressive multilingual voices at consumer-GPU speed.GitHub stars: 15k