Supertonic 3 — text to speech, ten voices in 31 languages, for xOllama

Supertonic 3 (f16 or Q8_0 GGUF) · audio.cpp engine · 10 voices · mp3 at 44.1 kHz · OpenAI /v1/audio/speech

Runs on xOllama, not on stock ollama. Stock ollama pulls this model but cannot show or run it: it carries only media engines. It needs: - an opencoti engine with the audio.cpp sidecar (dev build 2610030147001/b112 or later, set with XOLLAMA_ENGINE_PATH; the engine pinned by the current xOllama release has no media engines and refuses the model at load); - an xOllama built on or after 2026-10-03. audio.cpp tells a GGUF by its file name, and earlier builds hand it the model under its blob name, which it refuses.

Supertonic speaks ten voices, each in 31 languages, at 44.1 kHz. audio.cpp runs it on the CPU, so it needs no GPU.

Use

xollama pull mannix/supertonic:3
curl http://localhost:22434/v1/audio/speech \
  -d '{"model": "mannix/supertonic:3", "input": "The first ship came in at dawn.", "voice": "nova"}' -o speech.mp3
xollama media voices mannix/supertonic:3

Voices

Without a voice the template uses F1.

Measured

On bs2 (opencoti b112, audio.cpp on the CPU, 16 threads), a 21-word sentence:

Tags

3 is the default: the f16 file is the smaller of the two.

Source

GGUF: audio-cpp/audio.cpp-gguf · License: OpenRAIL. Docs: xOllama media.