Launching Tuesday: Sovereign Voice — on-device AI voice synthesis for Mac

Launching on Product Hunt this Tuesday (Aug 4).

Sovereign Voice is a Mac app that runs AI text-to-speech entirely on your machine. No cloud, no API keys, no per-character billing. The Qwen3-TTS model runs via MLX on your Apple Silicon GPU.

What it does:

- Type text, get audio. 5-9 seconds on an M4.

- Voice cloning from a short sample.

- Studio mode for long-form narration.

- Works fully offline after one-time model download.

Free: 25 generations, 1 voice.

Pro: $19 one-time, unlimited everything.

If you work with voiceover, narration, podcasts, or any audio content — I’d love your feedback. The product page has a demo video and full breakdown.

Happy to answer any questions about the architecture, the model, or the local-first approach.