The first launch of Kitten-TTS 2.

Kitten-TTS 2
Launching todayOpen-source text-to-speech that runs on CPU, from 4 MB
Free optionsArtificial IntelligenceAudioOpen Source
Meet the team
Hunted by Ilyas. The makers are not on 25launches yet.

Open-source text-to-speech that runs on CPU, from 4 MB
0 followers
Artificial IntelligenceAudioOpen Source
Kitten-TTS 2 is KittenML's family of text-to-speech models that run on a CPU. The new Pico (7M parameters, 4 MB per language in int4, 8 languages), Nano (17M) and Mini (82M, 16 languages, 118 voices) are Apache-2.0 ONNX models, installed with pip. The larger 1.7B model adds voice cloning from a few seconds of audio, emotion tags and 20 languages, but its license is free only below $1M in revenue and funding. KittenML also sells a hosted API.
The first launch of Kitten-TTS 2.

Open-source text-to-speech that runs on CPU, from 4 MB
Hunted by Ilyas. The makers are not on 25launches yet.