# FUTO releases ASR4ALL speech recognition models for CPU and mobile devices

> FUTO says it has released three streaming speech recognition models with 28 million, 56 million and 97 million parameters, designed for local CPU use.

- Canonical URL: https://newsverum.com/en/news/futo-asr4all-streaming-speech-models-cpu-mobile-2026
- Publisher: Newsverum
- Section: Technology
- Country: United States
- Published: 2026-10-15T17:36:41+00:00
- Updated: 2026-10-15T17:36:41+00:00
- Event / data period: 2026-10-13
- Other editions: [Türkçe](https://newsverum.com/tr/news/futo-asr4all-streaming-speech-models-cpu-mobile-2026.md), [العربية](https://newsverum.com/ar/news/futo-asr4all-streaming-speech-models-cpu-mobile-2026.md), [Français](https://newsverum.com/fr/news/futo-asr4all-streaming-speech-models-cpu-mobile-2026.md), [Español](https://newsverum.com/es/news/futo-asr4all-streaming-speech-models-cpu-mobile-2026.md), [Deutsch](https://newsverum.com/de/news/futo-asr4all-streaming-speech-models-cpu-mobile-2026.md), [Português](https://newsverum.com/pt/news/futo-asr4all-streaming-speech-models-cpu-mobile-2026.md)

FUTO announced ASR4ALL speech recognition models on October 13. The company said the small, medium and large versions contain 28 million, 56 million and 97 million parameters, respectively, and support streaming output while audio is being received.

FUTO says it designed the models to use ordinary CPU instructions and run locally. It also described a 5.3-million-parameter punctuation, capitalization and error-correction component called PCEC, plus a voice-activity detector that it says adds 2.5 thousand parameters. Training and performance statements are the company’s own reports, not independent benchmark findings.

## Data

### ASR4ALL model announcement

FUTO introduced three streaming ASR models for local CPU use; parameter counts are rounded figures reported by the company.

Methodology: Based on FUTO’s October 13 announcement. Parameter counts are rounded as reported by the source; no independent performance result is inferred.

| date | label | description | status |
|---|---|---|---|
| 2026-10-13 | FUTO announces ASR4ALL speech recognition models | FUTO introduced three streaming ASR models for local CPU use; parameter counts are rounded figures reported by the company. | occurred |

Sources: <https://futo.org/blog/asr4all> · Download data: [JSON](https://newsverum.com/api/v1/articles/futo-asr4all-streaming-speech-models-cpu-mobile-2026/data/announcement?lang=en&format=json) · [CSV](https://newsverum.com/api/v1/articles/futo-asr4all-streaming-speech-models-cpu-mobile-2026/data/announcement?lang=en&format=csv)

## Sources

- [FUTO](<https://futo.org/blog/asr4all>) (Source checked: 2026-10-15; Published: 2026-10-13)

---

Cite the canonical URL above. [Editorial standards and corrections](https://newsverum.com/en/editorial)