Model reference · open weights

supertonic-2

Available as managed deployment Audio Supertone Text→speech 1 variants 1k dl/mo

supertonic-2 is an open-weight audio or speech model from Supertone. AxForge deploys and operates it for you on dedicated EU-owned hardware — with the licence handled where one is required.

Available as managed deployment — configured and operated for you on dedicated EU hardware, quoted per deployment.

What it is

Released bySupertone
TypeAudio & music
TaskText→speech
Runs withsupertonic
Released2026-01-06
Popularity1k downloads / month
LicenceOpen weights

About

What supertonic-2 is

Supertonic is a lightning-fast, on-device text-to-speech system designed for extreme performance with minimal computational overhead. Powered by ONNX Runtime, it runs entirely on your device—no cloud, no API calls, no privacy concerns.

Read the full model card

What's New in Supertonic 2

Supertonic 2 extends multilingual capabilities while maintaining the same inference speed and efficiency as the original.

🌍 Multilingual Support

LanguageCode
Englishen
Koreanko
Spanishes
Portuguesept
Frenchfr

⚡ Same Speed, More Languages

  • No speed degradation: Supertonic 2 delivers the same ultra-fast inference speed as the original—up to 167× faster than real-time
  • Efficient architecture: Only 66M parameters, optimized for on-device deployment
  • Cross-language consistency: All supported languages share the same model architecture and inference pipeline

Performance

We evaluated Supertonic's performance (with 2 inference steps) using two key metrics across input texts of varying lengths: Short (59 chars), Mid (152 chars), and Long (266 chars).

Metrics:

  • Characters per Second: Measures throughput by dividing the number of input characters by the time required to generate audio. Higher is better.
  • Real-time Factor (RTF): Measures the time taken to synthesize audio relative to its duration. Lower is better (e.g., RTF of 0.1 means it takes 0.1 seconds to generate one second of audio).

Characters per Second

SystemShort (59 chars)Mid (152 chars)Long (266 chars)
Supertonic (M4 pro - CPU)91210481263
Supertonic (M4 pro - WebGPU)99618012509
Supertonic (RTX4090)2615654812164
API ElevenLabs Flash v2.5144209287
API OpenAI TTS-1375582
API Gemini 2.5 Flash TTS121824
API Supertone Sona speech 1386492
Open Kokoro104107117
Open NeuTTS Air374247

Notes: API = Cloud-based API services (measured from Seoul) Open = Open-source models Supertonic (M4 pro - CPU) and (M4 pro - WebGPU): Tested with ONNX Supertonic (RTX4090): Tested with PyTorch model Kokoro: Tested on M4 Pro CPU with ONNX NeuTTS Air: Tested on M4 Pro CPU with Q8-GGUF

Real-time Factor

SystemShort (59 chars)Mid (152 chars)Long (266 chars)
Supertonic (M4 pro - CPU)0.0150.0130.012
Supertonic (M4 pro - WebGPU)0.0140.0070.006
Supertonic (RTX4090)0.0050.0020.001
API ElevenLabs Flash v2.50.1330.0770.057
API OpenAI TTS-10.4710.3020.201
API Gemini 2.5 Flash TTS1.0600.6730.541
API Supertone Sona speech 10.3720.2060.163
Open Kokoro0.1440.1240.126
Open NeuTTS Air0.3900.3380.343

Characters per Second (5-step)

SystemShort (59 chars)Mid (152 chars)Long (266 chars)
Supertonic (M4 pro - CPU)596691850
Supertonic (M4 pro - WebGPU)57011181546
Supertonic (RTX4090)128637576242

Real-time Factor (5-step)

SystemShort (59 chars)Mid (152 chars)Long (266 chars)
Supertonic (M4 pro - CPU)0.0230.0190.018
Supertonic (M4 pro - WebGPU)0.0240.0120.010
Supertonic (RTX4090)0.0110.0040.002

License

This project’s sample code is released under the MIT License. - see the LICENSE for details.

The accompanying model is released under the OpenRAIL-M License. - see the LICENSE file for details.

This model was trained using PyTorch, which is licensed under the BSD 3-Clause License but is not redistributed with this project. - see the LICENSE for details.

Copyright (c) 2026 Supertone Inc.

From the published model card. Full card on the HuggingFace links in the sidebar.

How it works

How audio & music work

Audio or textinputAudio modelrecognise / synthesiseText or audiooutputSpeech-to-text turns audio into text; text-to-speech and music models turn text into audio.

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys supertonic-2 for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (supertonic-2 below is illustrative; you get the exact model name on deployment.)

$ curl -sS https://api.axforge.ai/v1/audio/transcriptions \
  -H "Authorization: Bearer $AXFORGE_API_KEY" \
  -F model="supertonic-2" -F file=@audio.mp3

Create an account — your API key is available in the console. 3M free tokens every 30 days with every new account.

© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms