SalamAI
Say it once. Everyone hears it in their own language.
One person speaks. SalamAI translates the speech live, plays it aloud, and shows subtitles. It runs in the browser, so the speaker and audience do not need to install an app.
Languages through the broader translation engine
Curated languages with spoken output today
Output languages in one live session
Session modes
Use the setup that matches the room.
One-way session
One speaker is translated aloud and captioned live for everyone listening.
Two-way conversation
Two people hold a live conversation using hands-free voice detection or push-to-talk.
Remote Speaker
A presenter joins by temporary browser link from their own phone and becomes the session microphone.
Companion Mode
The audience joins a listen link on their own phones for translated audio and synced subtitles.
After the session
Encrypted history, optional summaries, recordings, and a text-only caption mode for OBS are available.
Where it helps
For any room where people do not share one language.
Built around the multilingual reality of Malaysia and Asia Pacific.
Conferences and town halls
Translate one speaker into several live language channels for the room or a regional broadcast.
Clinics and public counters
Use two-way translation for a patient, visitor, applicant, or citizen conversation.
Worship and education
Provide spoken translation and readable subtitles for congregations, lectures, and campus events.
Tours and customer support
Let visitors or customers hear the speaker in their own language on a phone or browser.
How it works
Three steps. Nothing to install.
The browser sends audio directly to the speech model. Ordinexis servers handle sign-in, limits, and metadata, not plaintext voice.
Choose the source
Microphone, mixer, browser tab, app audio, or a remote speaker.
Choose languages
Select the output languages, volume, and audio device.
Start speaking
Subtitles appear first and spoken translation follows.
Share when needed
Open Companion Mode so the audience can listen on their phones.
Security and honest limits
Clear controls, with the trade-offs stated plainly.
Two-step sign-in, invite-only teams, database-enforced tenant isolation, and tamper-evident audit logs.
Transcripts and optional recordings are encrypted in the browser before upload. Search and playback decryption happen locally.
Provider credentials are short-lived and limited to one purpose. Remote Speaker credentials are temporary and single-use.
Companion Mode currently supports one-way sessions and has roughly 6 to 20 seconds of delivery delay.
Billing is based on active translated audio minutes, not seats, listeners, or silent wall-clock time.
See SalamAI in full.
The product site covers detailed features, architecture, security, and commercial options.
Start a useful conversation
Tell us what your team needs to improve.
Share the workflow, users, data, and result you have in mind. We will tell you what is practical and what it will take.
Email our team