Speech to text

Phonon

A very compact English speech recognition model: 164 MB, close in accuracy to its large Parakeet base. Transcribes an hour of audio in about 20 seconds on a laptop.

Developer
Fermion Research, not stated
First release
Sep 2026
Latest release
Sep 2026
Sizes
164 MB (about 2.1 bits per weight)
License
Commercial use allowedCC BY 4.0
Russian
Not supported
Running
On your own serverAlso runs without a GPU
Industries
Customer support, Media and production, Documents and accounting
Deploy on your server Hugging Face

What it does

  • transcribing English meetings and calls
  • dictating text on a laptop offline
  • subtitles for English videos

Where it is used

call centersmedia and podcastsoffice work

Hardware requirements

LaptopLaptop or regular PC, up to 8 GB of VRAM — smaller versions
fits
1 GPUOne GPU with 16–80 GB — mid-size versions
no versions
ClusterServer with several GPUs — flagship versions
no versions

Versions

  1. Phonon-2 (на базе Parakeet TDT 0.6B v3)

How to run it

On your own serverWeights are downloaded from Hugging Face and served with vLLM (load and API) or llama.cpp (modest hardware). The model then runs in a closed network with no per-request fees.Hugging Face
How much hardware you needCalculate the VRAM for the model size, context length and number of concurrent requests.Open the hardware calculator

I can set this up end to end: pick the model size, deploy it on your server and connect it to your systems.

Frequently asked questions

Can Phonon be used in a commercial project?

Yes. License: CC BY 4.0. It allows commercial use, but it is still worth having a lawyer review the license before launch.

What hardware does Phonon need?

At minimum: Laptop or regular PC, up to 8 GB of VRAM — smaller versions. Some versions also run on an ordinary CPU, without a GPU. You can calculate the exact VRAM for your model size and context in the hardware calculator.

Does Phonon support Russian?

No. The developer documentation lists the supported languages and Russian is not among them.

Where can I download Phonon and what does it cost?

The Phonon weights are open and free to download. You only pay for the hardware it runs on and for the setup. Source links are at the bottom of this page.

How I deploy it for clients

  1. SelectionI pick the model size for your task and hardware and test it on your examples.
  2. DeploymentI deploy it on your server or in a closed network and provide an API.
  3. Fine-tuningI fine-tune it on your data (LoRA) or connect a knowledge base — whichever is cheaper for the task.
  4. IntegrationI connect it to your CRM, ERP, bot, website or team chat and set up monitoring.

Similar models

Speech to textNVIDIA Parakeet / Canary / Nemotron SpeechNVIDIA · USACommercial use with conditions

Fast NVIDIA speech recognition models, including streaming ones for real-time use. Parakeet TDT v3 and Nemotron 3.5 ASR understand Russian.

DetailsSpeech to textWhisperOpenAI · USACommercial use allowed

Speech recognition in 99 languages, including Russian. The de facto standard for transcribing calls and meetings. Hugging Face's faster Distil-Whisper is English only.

DetailsSpeech to textMoonshineMoonshine AI (Useful Sensors) · USACommercial use allowed

Very small and fast speech recognition models for phones, tablets and embedded devices. Version 2 streams, producing text while the person is still speaking.

Details

Source: huggingface.co/FermionResearch/Phonon-2. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.