Phonon from Gradium.ai is a fantastic release. It is tiny (31M params), runs on-device with low latency, and the voice is super clear for something this small.
Now available in pipecat-local-tts-server v0.6.0: https://github.com/vr000m/pipecat-local-tts-server/
Bonus: supporting it meant bumping mlx-audio, which also sped up the other models by 14–20%.. h/t! blaizzy/mlx-audio team 🙏
GradiumReal-Time Voice AI API for Voice Agents | GradiumLow latency Text-to-Speech, Speech-to-Text, Voice Cloning and Voice Design. 50 ms to first audio, one API, start free.
commit c776e08