How it works
Three steps. Nothing to install.
Because this genuinely is a sequence — pick a source, pick a language, start talking — it's the one place on this page numbers earn their keep.
What are you translating?
A headset mic, a room mic, a mixer line-in, the audio from a browser tab or app, or a remote speaker joining by link from their own phone — even a mic and a tab mixed together with a live balance fader and a limiter so nothing clips.
Translate into
Pick up to five output languages at once, from a curated set of 13 that speak aloud in a steady voice, or a reach of 100 for text and regional-accent control. Each output gets its own volume, mute, solo and audio device.
Start
Audio streams straight from the browser to the AI speech model — subtitles appear immediately, spoken translation follows a beat behind. Auto-stop after silence means a forgotten tab doesn't quietly keep billing.
Your browser
Microphone or tab audioAI speech model
One of two engines, directQuick overview
Every feature, at a glance.
Six ways to shape a session — pick the one your room needs, or mix more than one.
Foundation
One Way
One speaker, translated aloud and captioned live for everyone listening — the original Salam.AI session.
Learn more →
Real conversation
Two Way
A real back-and-forth, hands-free or push-to-talk, for a live conversation between two people.
Learn more →
Reaches every phone
Companion Mode
Turn any session into a listen link your whole audience joins from their own phone.
Learn more →
No equipment
Remote Speaker
A presenter anywhere becomes your microphone — joins by link from their own phone, no extra hardware.
Learn more →
After the mic goes off
Beyond the session
Private encrypted history, post-session summaries, and a lighter text-only engine for captions.
Learn more →
What it never sees
Security & trust
Encrypted by default, tenant-isolated, audited — and never a long-lived provider key.
Learn more →