What is EdgeSpeak?
EdgeSpeak is a desktop speech app for local audio and video transcription, with CLI and gateway workflows for trusted tools on the same computer.
FAQ
EdgeSpeak questions, answered plainly.
Use this page when you want the short version of what EdgeSpeak does today, how local transcription works, and where CLI, agents, and licensing fit.
Direct answer
EdgeSpeak is a desktop speech app that runs its speech engine locally for audio and video transcription. It also provides CLI and local gateway workflows for trusted tools and AI agents on the same computer.
Short product definition
EdgeSpeak is local-first speech software for desktop transcription, transcript review, export, CLI automation, and local agent workflows.
FAQ
How does EdgeSpeak process speech locally?
EdgeSpeak runs a bundled speech engine on the device. The homepage model section explains the model family used for local transcription.
Does EdgeSpeak support video transcription?
Yes. The current desktop workflow supports importing audio or video and producing transcripts for review and export.
Can command-line tools use EdgeSpeak?
Yes. The EdgeSpeak CLI can transcribe local files and talk to the local gateway when the desktop app is ready.
Can AI agents use EdgeSpeak?
Yes. Skills-capable agents can use the public EdgeSpeak Agent Skill and call edgespeak-cli for local transcription tasks.
What platforms are available today?
The current public desktop download is macOS-first. Windows is planned but should be described as coming soon until it is available.
How many devices are included?
The lifetime license is currently positioned for up to four activated devices.