Model reference · open weights

MioCodec-25Hz-44.1kHz

MioCodec-25Hz-44.1kHz is an open-weight audio or speech model from Aratako, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.

Audio Aratako 1 variants 181k downloads/mo
Request this model on EU hardware All served models Not on the shared API today — deployed on request.

About

What MioCodec-25Hz-44.1kHz is

MioCodec-25Hz-44.1kHz-v2: Lightweight Neural Audio Codec for Efficient Spoken Language Modeling [](https://github.com/Aratako/MioCodec) MioCodec-25Hz-44.1kHz-v2 is an upsampled, high-fidelity version of the MioCodec-25Hz-24kHz model. By integrating an UpsamplerBlock inspired by Inworld TTS-1 into the decoder, this model reconstructs 44.1 kHz audio from the standard 25 Hz token stream. 🌟 What's New in v2 This model is a fine-tuned version of MioCodec-25Hz-24kHz with the following architectural enhancements: 44.1 kHz Output: Achieves higher audio fidelity compared to the base 24 kHz model. UpsamplerBlock + SnakeBeta: We adopted the UpsamplerBlock architecture from Inworld TTS-1 and enhanced it by integrating SnakeBeta activations. This combination allows the decoder to effectively predict and generate high-frequency components, enabling clear 44.1 kHz reconstruction from the lower-resolution input. Token Compatibility: During fine-tuning, the content branch was frozen. This means the discrete tokens generated by this model are identical to those from MioCodec-25Hz-24kHz. You can take any TTS model trained on the 24kHz tokens and simply swap the codec to this v2 model during inference to instantly upgrade the audio quality to 44.1 kHz. 📊 Model Comparison 🚀 Quick Start Installation Basic Inference Basic usage for encoding and decoding audio: Voice Conversion (Zero-shot) MioCodec allows you to swap speaker identities by combining the content tokens of a source with the global embedding of a reference. 📜 Acknowledgements Codec Architecture: Based on the brilliant work of kanade-tokenizer. Decoder Design: Inspired by XCodec2 and Inworld TTS-1. 🖊️ Citation

Summarised from the published model card. Read the full card on the HuggingFace links below.

Specifications

What it is

MakerAratako
TypeAudio & music
Parameters (lead)132M
Variants1
Based onAratako/MioCodec-25Hz-24kHz
Released2026-02-14
Popularity181k downloads / month
Likes11
LicenceOpen weights

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.

Variants

Sizes & precisions

Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.

VariantParamsPrecisionVRAMFits 16 GBWeights
MioCodec-25Hz-44.1kHz-v2132MBF16~0.3 GBWeights ↗

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys miocodec-25hz-44-1khz for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (miocodec-25hz-44-1khz 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="miocodec-25hz-44-1khz" -F file=@audio.mp3

Details

Languages, data & research

Languages

en ja nl fr de it pl pt es ko zh

Trained / evaluated on

sarulab-speech/mls_sidon mythicinfinity/Libriheavy-HQ nvidia/hifitts-2

Tags

safetensors speech audio tokenizer audio-to-audio en ja nl fr de it pl pt es

Papers

Licence

Open weights

Open weights under mit — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗

Sources

Weights & code

Want MioCodec-25Hz-44.1kHz on EU-owned hardware?

Request this model on EU hardware See what’s served now

Explore

More audio & music

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