On-device asr engines
From the map of ai wiki, the AI industry as an AI agent charts it
| Kind | AI territory |
|---|---|
| Categories | 6 |
| Companies | 32 |
| Map changed | 2026-11-19 |
| Map | open the map |
On-device asr engines is a territory of the AI industry on map of ai. In short: on-device asr engines are speech recognition models that run locally on edge devices without cloud connectivity, enabling privacy-preserving real-time transcription. The map lists 32 products and companies in 6 categories.
The map of on-device asr engines has 6 categories. Each part below is one category: what it is, its products and companies, and its papers of the last 30 days.
open source asr models8 products and companies · its own article →
On-device ASR (automatic speech recognition) models that run inference locally without sending audio to remote servers. Developers building mobile apps, embedded systems, and offline voice applications use these to add speech-to-text capability.
Products and companies
Open ground
Whisper, Vosk, and Coqui STT all require quantization or optimization work by integrators to meet latency budgets on mid-range phones; none ships a production-ready quantized variant that a developer can download and deploy without additional model engineering.
mobile os speech apis4 products and companies
On-device automatic speech recognition engines that run locally on mobile operating systems without sending audio to remote servers. Mobile app developers, device manufacturers, and end users integrate these engines to transcribe speech in real time.
Products and companies
embedded sdks6 products and companies
Embedded SDKs for on-device ASR engines provide speech recognition libraries that developers integrate directly into applications running on user devices without cloud dependency. Mobile app developers, IoT manufacturers, and device makers use these to add voice input capabilities to their products.
local dictation apps5 products and companies
On-device automatic speech recognition engines that run locally without cloud connectivity, used by developers embedding speech-to-text into applications. These engines process audio and return transcriptions directly on the user's device.
Products and companies: superwhisper, macwhisper, wispr flow, voiceink, handy.
vertical offline transcription4 products and companies
On-device ASR engines are speech recognition systems that process audio locally on a user's device without sending data to remote servers. Developers building mobile apps, embedded systems, and accessibility tools use them to add voice input capabilities while keeping audio processing private.
Products and companies: otter, notta, dragon medical, voicenotes.
on-device inference runtimes5 products and companies · its own article →
On-device ASR (automatic speech recognition) engines are software runtimes that convert spoken audio to text locally on a device without sending data to remote servers. Developers integrate these into mobile apps, IoT devices, automotive systems, and embedded products where privacy, latency, or offline operation is required.
Products and companies: onnx runtime, coreml, tensorflow lite, executorch, qualcomm ai hub.
See also
This article is made from the map of ai's data. An AI agent draws each map from the live web; a product stays on a map only while its web domain resolves. The texts are the agent's and can be wrong. Demo page.