Otosaku/OtosakuStreamingASR-iOS

OtosakuStreamingASR-iOS is a real-time speech recognition engine for iOS, built with Swift and Core ML. It uses a fast and lightweight streaming Conformer model optimized for on-device inference. Designed for developers who need efficient audio transcription on mobile.

29
/ 100
Experimental

OtosakuStreamingASR-iOS is for iOS developers who need to add real-time speech recognition directly into their mobile applications. It takes live audio input from an iPhone or iPad and converts it into transcribed text, all processed on the device itself. This is ideal for building privacy-focused apps that require voice-to-text functionality.

No commits in the last 6 months.

Use this if you are an iOS developer building an app that needs to transcribe Russian speech in real-time, offline, and entirely on the user's device.

Not ideal if you need a cloud-based speech recognition service, support for languages other than Russian (without custom fine-tuning), or are not an iOS developer.

iOS development mobile app speech-to-text privacy-first on-device processing
No License Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 5 / 25
Maturity 7 / 25
Community 15 / 25

How are scores calculated?

Stars

11

Forks

4

Language

Swift

License

Last pushed

Jun 14, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/Otosaku/OtosakuStreamingASR-iOS"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.