Speech to text

Granite Speech

IBM speech models for recognizing and translating speech in English, several European languages and Japanese. Designed for enterprise use.

Developer
IBM, USA
First release
Mar 2025
Latest release
Aug 2026
Sizes
470M – 8B
License
Commercial use allowedApache 2.0 (the granite-speech-5.0-470m-turboctc-nc variant is non-commercial)
Russian
Not supported
Ready-made builds
GGUF
Running
On your own serverAlso runs without a GPU
Industries
Customer support, Finance, Documents and accounting
Deploy on your server Hugging Face

What it does

  • Transcribing business meetings
  • Translating speech into text in another language
  • Voice assistants
  • Processing call recordings

Where it is used

Large companiesCall centersFinanceInternational teams

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
fits
ClusterServer with several GPUs — flagship versions
no versions

Versions

  1. Granite Speech 5.0 470M
  2. Granite Speech 4.1 2B
  3. Granite 4.0 1B Speech
  4. Granite Speech 3.3 2B и 8B
  5. Granite Speech 3.2 8B

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. Quantization compresses a model so it takes less video memory and runs on more modest hardware. Answers change slightly, so quality is checked on your own examples.

Frequently asked questions

Can Granite Speech be used in a commercial project?

Yes. License: Apache 2.0 (the granite-speech-5.0-470m-turboctc-nc variant is non-commercial). It allows commercial use, but it is still worth having a lawyer review the license before launch.

What hardware does Granite Speech 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 Granite Speech support Russian?

No. The model card lists its languages and Russian is not among them.

Where can I download Granite Speech and what does it cost?

The Granite Speech 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 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 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.

DetailsTextIBM GraniteIBM · USACommercial use allowed

IBM enterprise models with transparent training data and ISO 42001 certification. Granite 4 is a memory-efficient Mamba and Transformer hybrid.

Details

Source: huggingface.co/ibm-granite/granite-speech-5.0-470m-turboctc. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.