On-Device Speech-to-Text is a speech recognition offering for Mac and Windows that processes audio locally.
On-Device Speech-to-Text runs speech recognition locally on Mac and Windows machines, so audio never leaves the device while delivering accuracy positioned at cloud-grade quality, with support for multiple languages and speaker diarization.
It is aimed at deployment contexts where offline operation, data privacy, or low latency matter, including on-site transcription, regulated environments, and applications that cannot depend on a network connection.
Deepgram
Deepgram Self-Hosted Speech-to-Text
deepgram.com
Superwhisper
Superwhisper — Voice Dictation
superwhisper.com
Willow
Willow Voice
willowvoice.com
| Attribute | On-Device Speech-to-Text | Deepgram Self-Hosted Speech-to-Text | Superwhisper — Voice Dictation | Willow Voice | |
|---|---|---|---|---|---|
| Provider |  | | | | |
| Founded | 2006 | 2015 | — | 2025 | |
| Sells To | — | Enterprise, Small Business | — | — | |
| Pricing Model | Recurring Subscription | Recurring, Software, Usage-based | — | — | |
| Ownership | Private | Venture-backed | — | — |
Provider
Founded 2006
Sells To —
Pricing Model Recurring Subscription
Ownership Private
Provider
Founded 2015
Sells To Enterprise, Small Business
Pricing Model Recurring, Software, Usage-based
Ownership Venture-backed
Provider
Founded —
Sells To —
Pricing Model —
Ownership —
Provider
Founded 2025
Sells To —
Pricing Model —
Ownership —
Deepgram's Speech-to-Text API is a conversational speech recognition service in real-time and pre-recorded modes.
AssemblyAI's Speech-to-Text API transcribes audio in streaming and pre-recorded modes with speaker diarization.
Voice-to-text software that turns speech into formatted writing across apps.
Deepgram's Text-to-Speech API generates streamed spoken audio for enterprise voice-agent applications.
Voice-to-text software that turns spoken words into formatted writing in any app.
macOS app that translates live audio in Zoom, Meet, Teams, and other meeting tools without meeting bots or extra invites.
Developer API for streaming real-time speech-to-speech translation and dubbing over WebSocket.
Developer platform providing real-time and batch APIs for speech-to-text, text-to-speech, and voice agents.
AI transcription platform that produces live rough-draft transcripts with speaker identification for court reporters and legal transcriptionists.
OpenAI Realtime API provides conversational speech-to-speech models for developers building interactive voice agents.
Amazon Nova Sonic provides streaming speech-to-speech models for conversational applications and voice assistants.
Developer API platform for production-ready speech, transcription, music, agents, and audio generation.
Deepgram's Speech-to-Text API is a conversational speech recognition service in real-time and pre-recorded modes.
AssemblyAI's Speech-to-Text API transcribes audio in streaming and pre-recorded modes with speaker diarization.
Voice-to-text software that turns speech into formatted writing across apps.
Deepgram's Text-to-Speech API generates streamed spoken audio for enterprise voice-agent applications.
Voice-to-text software that turns spoken words into formatted writing in any app.
macOS app that translates live audio in Zoom, Meet, Teams, and other meeting tools without meeting bots or extra invites.
Developer API for streaming real-time speech-to-speech translation and dubbing over WebSocket.
Developer platform providing real-time and batch APIs for speech-to-text, text-to-speech, and voice agents.
AI transcription platform that produces live rough-draft transcripts with speaker identification for court reporters and legal transcriptionists.
OpenAI Realtime API provides conversational speech-to-speech models for developers building interactive voice agents.
Amazon Nova Sonic provides streaming speech-to-speech models for conversational applications and voice assistants.
Developer API platform for production-ready speech, transcription, music, agents, and audio generation.
