Cross-app dictation
Speak text into compatible applications rather than switching to a separate writing workflow.
Newsletter
Join the Community
Subscribe to our newsletter for the latest news and updates
Open-source dictation and transcription for desktop and iOS, with local speech models, offline operation and optional cloud transcription.
专业的DDSM批量二维码生成工具，在线快速生成多个高质量二维码，支持自定义样式、格式导出与打包下载。
Speak text into compatible applications rather than switching to a separate writing workflow.
Run supported speech-to-text models on your device for local dictation and offline use.
Auto-detect speech across more than 100 languages, according to the official site.
Refine dictated text with voice instructions and improve recognition of names or domain terms.
Draft messages, notes and documents with voice input.
Capture and transcribe meetings without adding a meeting bot, using the configured workflow.
Use local models when you want transcription to remain on your device.
OpenWhispr is an open-source voice dictation and transcription app for macOS, Windows, Linux and iOS. It converts speech to text across applications and can capture meeting notes or transcribe uploaded audio. Local speech models support on-device processing and offline use; users may also configure cloud transcription or their own API keys.
The product includes AI text cleanup, voice instructions, vocabulary learning from corrections and support for more than 100 languages. The project is published under the MIT license. The website states local dictation stays on the device, while cloud recordings are deleted after transcription completes; review current privacy details and configuration before enabling cloud features.
Use the download for your operating system, choose an available local model or configure a provider, then dictate into the application you are working in.
