Real-time AI interpreting for macOS
Strym turns your Mac into a simultaneous interpreter: speak your language, and your audience hears a natural voice in theirs, live on Zoom, Google Meet and beyond. Two-way translation, in real time.
Two modes, one tool
Webinar · one-way
Lectures, presentations and live streams: your voice is transcribed, translated and re-voiced by AI. Your audience hears a smooth, real-time translation.
You speak → Strym translates → your audience listens
Conversation · two-way
Meetings, negotiations and consultations: Strym translates both ways in real time. You speak your language, they hear theirs, and vice versa, inside a normal video call.
You ↔ them · each in your own language
How it works
Deepgram Nova: state-of-the-art speech-to-text with specialised models for meetings, medical and financial terminology.
Choose your engine (Groq, Claude or Gemini) and set a backup order. If one provider fails, another takes over automatically, so no sentence is lost.
Hundreds of natural voices by Cartesia and ElevenLabs, filtered by language, for both the voice you send and the one you hear.
Features that make the difference
English, Spanish (4 variants), Italian, French, German, Chinese, Japanese, Arabic and more.
Your field's terminology, translated your way, in both directions. Load it from a file.
Teach speech recognition your names, acronyms and jargon, so they are understood on the first try.
Headphones, speakers and a virtual device with independent volumes. Bluetooth headsets re-attach on their own.
Per-stage latency and session cost in real time, item by item.
Save the session's translated audio in one click, ready to share.
Auto-reconnect and a Mac that never falls asleep: a 3-hour call is business as usual.
Your tone, style and rules on top of a hardened base that only ever translates.
Privacy & costs
Strym connects directly to the AI providers with your personal API keys. Your voice never touches our servers: Mac → provider → platform. Period.
You pay providers only for real usage: a one-hour call typically costs a euro or two in API fees. The in-app meter shows it live.
Switch models or providers anytime, even with a custom model ID, the day it ships. Guided onboarding handles the rest.
Who Strym is for
Courses open to an international audience, no interpreter required.
Serve clients abroad in their own language.
Meetings without broken English getting in the way.
Reach viewers well beyond your own language.
FAQ
No. Everything runs on your Mac. For them it's a regular Zoom, Meet or Webex call, with a voice that happens to speak their language.
About one second from the end of your sentence to the spoken translation: the rhythm of a simultaneous interpreter. The stats panel shows the real numbers for every stage.
A Mac, API keys from the providers (free to create, most include starter credits) and the free BlackHole audio driver. The setup wizard walks you through it.
With any software that lets you choose a microphone and a speaker: Zoom, Google Meet, Webex, Teams, Discord, OBS and more.
Your audio goes directly to the AI providers you chose, with your own keys. Strym has no servers listening, recording or storing anything.
Coming soon
Leave your address and we write once, when Strym is ready to download.
One email, nothing else, no sharing.
