TTS.ai
Twenty-seven open-source TTS models in one UI with no signup required for the free tier.

300M TTS model running locally on consumer GPU or Apple Silicon.
AI developers
OpenAI Voice · Deepgram · Whisper
Twenty-seven open-source TTS models in one UI with no signup required for the free tier.
5.6x realtime on CPU with voice cloning beats most local TTS options.
Shrinks the usual TTS bloat into a 16MB Electron-alternative wrapper while still letting you clone voices from a short sample and 'design' voices from text prompts. It handles model downloads for you, supports batch exports and macOS auto-updates — smart product trade-offs. Caveat: the app binary is tiny, but the underlying TTS models are downloaded on demand, so expect large model pulls behind the scenes.
Voice cloning on ESP32 without cloud beats Yoto's subscription model completely.
Voice agent orchestration with no-code studio, but orchestrates off-the-shelf APIs like everyone else.
Kokoro voice cloning with multilingual support, but voice cloning itself is crowded.