Kitten TTS 2 Mini is a free, Apache 2.0 AI voice generator: 118 voices in 16 languages from an 82.7 MB file that runs on CPU. Setup, comparison and catches.
ZONOS3-Mini is a free, Apache 2.0 AI voice cloner that runs in your browser via WebGPU. Here are the real specs, setup commands, and the benchmark catch.
Maya 2 Native is a free Apache 2.0 TTS model for 11 Indian languages plus English, with voice cloning, a free demo and a 12 GB GPU local setup.
Phonon TTS is a free, Apache 2.0 voice model from Gradium: 65 MB, no GPU, runs in a browser tab. Our speed test, exact commands, and the license catch.
KittenTTS 2 clones a voice from a 5-second clip and runs on a laptop CPU. Free demo, pip install, real speed test, and the license catch for creators.
Fish Audio Drama 3 clones voices, casts 16-character scenes and takes direction. Try it free in a Hugging Face Space, plus the license and 48 GB GPU catch.
Suno Speech makes narration and music in one take, free to try. Here's how to use it, and how to build an open-source version with Kokoro, ACE-Step and ffmpeg.
Sopro V2 Turbo is a free, Apache-2.0 voice cloner that copies a voice from 5-20 seconds of audio and runs on a laptop CPU or right in your browser.
Eleven v4 tops the independent TTS arena. Here's how to try ElevenLabs' new AI voice model free today, plus Apache and MIT open-source alternatives.
Gemini 3.8 Flash TTS designs new AI voices from a text prompt and is free in Google AI Studio. Pricing, limits, code, and the open Qwen3-TTS alternative.