mannix/ supertonic:3

102 Downloads Updated 4 weeks ago

Supertonic 3 · audio.cpp engine · 10 voices · mp3 at 44.1 kHz

ollama run mannix/supertonic:3

curl http://localhost:11434/api/chat \
  -d '{
    "model": "mannix/supertonic:3",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='mannix/supertonic:3',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'mannix/supertonic:3',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 4 weeks ago

4 weeks ago

43f403a6d65e · 313MB

json

{"version":7,"media":{"tts":{"engine":"audiocpp","model":"sha256:b312b57797d40ac5c09d915893dbdbaf640

274B

Readme

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.

OpenAI	Supertonic
`alloy`	`F1`
`echo`	`M1`
`fable`	`M2`
`onyx`	`M3`
`nova`	`F2`
`shimmer`	`F3`

Measured

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

Tag	first request, engine start included	output	Whisper on the output
`3` (f16)	4.8 s	8.0 s of mp3, 44.1 kHz	word for word
`3-q8_0`	6.7 s	8.0 s of mp3, 44.1 kHz	word for word

Tags

Tag	Weights	Size
`3`	`supertonic-3-f16.gguf`	313 MB
`3-q8_0`	`supertonic-3-q8_0.gguf`, the file opencoti’s gate ran	454 MB

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.

# 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](https://github.com/mann1x/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](https://huggingface.co/ManniX-ITA/opencoti-llamafile) 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

```shell
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`**.

| OpenAI | Supertonic |
|---|---|
| `alloy` | `F1` |
| `echo` | `M1` |
| `fable` | `M2` |
| `onyx` | `M3` |
| `nova` | `F2` |
| `shimmer` | `F3` |

## Measured

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

| Tag | first request, engine start included | output | Whisper on the output |
|---|---|---|---|
| `3` (f16) | 4.8 s | 8.0 s of mp3, 44.1 kHz | word for word |
| `3-q8_0` | 6.7 s | 8.0 s of mp3, 44.1 kHz | word for word |

## Tags

| Tag | Weights | Size |
|---|---|---|
| `3` | `supertonic-3-f16.gguf` | 313 MB |
| `3-q8_0` | `supertonic-3-q8_0.gguf`, the file opencoti's gate ran | 454 MB |

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

## Source

GGUF: [audio-cpp/audio.cpp-gguf](https://huggingface.co/audio-cpp/audio.cpp-gguf/tree/main/Supertonic-3-GGUF) · License: OpenRAIL.
Docs: [xOllama media](https://github.com/mann1x/xollama/blob/dev/docs/xollama/media.mdx).

Paste, drop or click to upload images (.png, .jpeg, .jpg, .svg, .gif)