Anyone. Anywhere.
Understood.
Real-time speech translation and live multilingual captions for conferences, meetings, and events.
No installation, no hardware, no interpreters. Attendees follow in their own language, instantly.
Trusted by leading organizations
Real-time speech translation for any audience
Multilingual conferences, hybrid meetings, live events, and presentations. Attendees follow along in their own language, instantly.
Conferences and live events
Speakers present in one language. Attendees choose from 80+ languages and follow live captions on their own device. No interpreter booth required.
Hybrid and remote meetings
Bridge language barriers across distributed teams. Real-time speech-to-text and translation so every participant stays in sync, regardless of location.
Webinars and online presentations
Reach a global audience without the cost of professional interpreters. Attendees join with a simple code: no app download, no hardware setup.
Custom glossary and pronunciation
Add your brand names, product terms, and acronyms. If the voice mispronounces one, set exactly how it should sound and preview it by ear before going live. Takes effect immediately, even during a live session.
PowerPoint add-in
Start a ProxVox session directly from your PowerPoint presentation. One click activates live speech translation for your audience without switching apps.
Native iPhone app for attendees
Attendees can join your session through the ProxVox iPhone app for a seamless listening experience. Audio plays in the background, notifications keep them in sync, and there is nothing to set up beyond a simple session code.
Ready to break the language barrier?
Ready the moment you are
No setup calls. No IT tickets. No training sessions. ProxVox works on day one, for everyone in the room.
Live in under a minute
Open a browser, click Start, share a code. No installation, no hardware, no IT department required. Your session is live before anyone opens a slide deck.
No AI training required
ProxVox uses zero-shot AI. You do not train a model, upload audio samples, or wait weeks for accuracy to improve. There is no AI training cost. It works from the first word.
Attendees need nothing
A session code or QR scan is all it takes. No account, no app download, no instructions to send in advance. Attendees are listening in their language within seconds.
What a multilingual event usually costs
Interpreters are booked in pairs, per language, per day. Every language you add means another pair. With ProxVox, every language is already included.
Simple, transparent pricing
Start free, then pay only for what you use. No subscription. Minutes never expire.
Entry
One or two speaking languages, 8 listening languages- 30 minutes, once per account
- Up to 3 speaking languages
- Up to 3 attendees
- 80+ listening languages
- Session transcripts included
- iPhone attendee app included
- Brand glossary (5 terms)
- 2 hours (120 min)
- 1 speaking language
- Up to 25 attendees
- 8 standard listening languages
- Session transcripts included
- Brand glossary (5 terms)
- Minutes never expire
- 10 hours (600 min)
- 2 speaking languages
- Up to 50 attendees
- 8 standard listening languages
- Session transcripts included
- Brand glossary (10 terms)
- Minutes never expire
Capability
All 80+ listening languages, iPhone attendee app, PowerPoint add-in- 20 hours (1,200 min)
- Up to 3 speaking languages
- Up to 100 attendees
- All 80+ listening languages
- Brand glossary with pronunciation control (100 terms)
- Minutes never expire
- iPhone app for attendees
- PowerPoint add-in
- 40 hours (2,400 min)
- Up to 4 speaking languages
- Up to 200 attendees
- All 80+ listening languages
- Brand glossary with pronunciation control (500 terms)
- iPhone attendee app, PowerPoint add-in
- Regional dialects, including Latin American Spanish
- Premium translation engine
- Co-presenter: pass the mic to 1 guest speaker
- 70 hours (4,200 min)
- Everything in Event
- Up to 5 speaking languages
- Up to 300 attendees
- Brand glossary with pronunciation control (1,000 terms)
- Co-presenters: pass the mic to up to 10 speakers (Event includes 1)
No per-attendee fees at any tier. Every listening language is included. Prepaid credits, no subscription, and they never expire.
Built for events that cannot afford to be misunderstood
Six capabilities you will not find bundled together, and exactly which plans include them.
Your brand names, said correctly
A fully customisable glossary for the terms that matter: list the mishearings to catch and keep product names untranslated in every language. From Pro upwards, set pronunciation precisely with IPA phonetics and hear a preview before you go live.
80+ languages, including regional dialects
Every listening language is included in the price, with no per-language charge. Event and Growth add true regional variants such as Latin American Spanish, so audiences hear the Spanish they actually speak rather than a European approximation.
Every attendee reads in their own language
One speaker, many languages at once. Attendees join with a link or QR code on any device, pick their language, and follow live captions. Up to 300 people in a single session, and no per-attendee fee at any plan.
iPhone app for hands-free listening
Attendees listen through a native app instead of a browser tab. Audio keeps playing in the background and on the lock screen, so phones go back in pockets and hands stay free for the rest of the session.
Works in the room and online
The same session covers an auditorium, a video call, or both at once. Nothing to install for attendees and no hardware to rent or wire. Presenting from slides? The PowerPoint add-in puts live captions over the deck you are already showing.
Pass the mic, even to a remote speaker
Hand live control to a panellist in the room or a co-presenter on another continent, without ending the session. Each joins by link, and translation continues uninterrupted through the handover. Event includes one guest speaker; Growth allows up to 10.
- Credits never expire Buy hours once and use them whenever your events happen.
- No subscription Prepaid credit, no monthly commitment, no annual minimum.
- No per-attendee fees Your audience can grow without the price changing.
Compare every plan
| Micro | Starter | Pro | Event | Growth | |
|---|---|---|---|---|---|
| Price | $99 | $580 | $1,500 | $2,800 | $4,200 |
| Hours included | 2 | 10 | 20 | 40 | 70 |
| Rate per hour | $49.50 | $58 | $75 | $70 | $60 |
| Speaking languages | 1 | 2 | 3 | 4 | 5 |
| Listening languages | 8 | 8 | 80+ | 80+ | 80+ |
| Attendees | 25 | 50 | 100 | 200 | 300 |
| Brand glossary terms | 5 | 10 | 100 | 500 | 1,000 |
| Brand glossary | Yes | Yes | Yes | Yes | Yes |
| IPA pronunciation control | No | No | Yes | Yes | Yes |
| Session transcripts | Yes | Yes | Yes | Yes | Yes |
| iPhone attendee app | No | No | Yes | Yes | Yes |
| PowerPoint add-in | No | No | Yes | Yes | Yes |
| Regional dialects (LatAm Spanish) | No | No | No | Yes | Yes |
| Co-presenters | No | No | No | 1 | Up to 10 |
| Credits expire | Never | Never | Never | Never | Never |
How does real-time conference translation work?
ProxVox captures the presenter's speech, converts it to text, and translates it into 80+ languages simultaneously. Attendees join via a URL or QR code on any device and read live captions in their chosen language. No hardware or interpreter is required.
Do attendees need to download an app?
No. Attendees join through any web browser using a session code or QR code. A native iPhone app is also available for a dedicated listening experience with background audio.
How many languages does ProxVox support?
ProxVox supports 80+ target languages including regional dialects. Presenters can speak in up to 5 source languages simultaneously depending on the plan.
Is ProxVox a replacement for a professional interpreter?
ProxVox provides AI-powered real-time caption translation and is well suited for conferences, corporate meetings, webinars, and events where live captioning in multiple languages is needed. For legal or diplomatic proceedings requiring certified interpretation, a professional interpreter is still recommended.
What should I do if a brand name or product term is mispronounced in the live captions?
ProxVox lets you add brand names, product terms, and acronyms to a custom glossary. On Pro plans and above, you can specify exactly how each term should sound using IPA phoneme notation, then listen to a preview before your event goes live. Changes take effect immediately, even during an active session.
Can I test whether the system will recognise my custom terms correctly?
Yes. ProxVox includes a glossary validation tool where you can speak your custom terms aloud and see how the speech-to-text engine interprets them in real time. If a term is not being recognised correctly, you can adjust the pronunciation and test again until it is accurate.
What counts as a "minute"?
One minute is deducted per wall-clock minute while your session is running. Billing pauses automatically after 5 minutes of silence, when you use Coffee Break, or when you disconnect. Unused prepaid minutes are always refunded at the end of your session.
Do my prepaid minutes expire?
Never. Unlike competitors, your minutes stay in your account indefinitely. Use them whenever you need them.
What's the difference between source and target languages?
The source language is what the presenter speaks (1 with Micro, 2 with Starter, up to 3 with Pro, up to 4 with Event, up to 5 with Growth). The target language is what each attendee chooses to hear. Micro, Starter, and Pro include 8 standard languages (English, Spanish, Portuguese, French, German, Chinese, Japanese, Italian). Event and Growth unlock all 81 languages, including regional dialects.
Can I try before buying?
Yes. Every account gets one free 30-minute demo: a fully functional session with up to 3 source languages, up to 3 attendees, all 81 target languages, and the iPhone attendee app. No card required. After the demo, pick a paid package to keep going.