Updated 14 November 2026
AI live interpretation for events
For events, Espero provides AI live interpretation: the speaker talks in their own language, and each guest reads live captions or listens to an AI voice in their own language on their own phone, joining by QR code or link with no app or account.
Try 7 hours free, with no card needed.
What AI live interpretation is
For real-time translation at an event, Espero combines speech recognition, translation, AI captions and an AI-generated voice. The speaker talks in their own language, and each guest follows in theirs.
Use live translation alongside human interpreters where you have them. Espero brings in every other language, including those no interpreter is available for.
How it works at your event
- Create your event and choose the languages for the broadcast. Organizers use Espero on iOS, Android and the web.
- Connect the sound: use the device microphone, a mixer over USB or Dante, or a computer audio source.
- Share the event’s QR code or viewing link. Print a QR poster or choose Show the QR on the big screen in the organizer view. A recurring event keeps the same QR code every time.
- Guests open the link in their browser, choose their language and read or listen on their own phone or computer. No app or account is needed to follow the translation.
What your guests get
Guests read captions in their chosen language. Many languages also offer an AI-generated voice; headphones let guests listen without disturbing others. When the only speaker broadcasts from their own account with My voice set up, guests can listen in an AI voice made from that speaker’s voice.
Every event has its own group conversation before, during and after, with questions in each person’s language. The organizer can show a question on the projector without the sender’s name. Joining the group needs a free Espero account; an email address is enough, and the organizer decides who can join. Return to listening takes a member back to the captions.
Message to listeners shows a practical note of up to 280 characters to people following the captions. The note appears as written.
Sound, screen and stream
One phone is enough to run the captions. Use its microphone, a mixer over USB or Dante, or a computer audio source. The preparation checklist marks a step done only when it works. A hint helps you check the sound when no speech comes through, and a note appears when the speech seems to be in another language.
Projector view shows large captions on the venue screen in the chosen language, with adjustable text size.
Stream caption overlay gives a transparent caption page for each language to add to OBS, vMix or ProPresenter as a browser source. Choose the lines, size, position and colour.
The link for stream viewers lets people watching a livestream read and listen in their own language in time with the stream. Captions and the AI voice wait for the stream’s delay, and each viewer can fine-tune it with Set by listening.
100+ languages and room for your audience
Choose from a 106-language catalog. A broadcast holds up to 10 languages at once, the spoken language included. Captions can be read in every catalog language, and many languages can also be listened to with an AI-generated voice. North Sami is caption-only.
Up to 400 listeners per event are included. Organizations can request an annual agreement for events with more than 400 listeners. Listeners using the same language share the translation.
Several speakers can speak different languages. Add an interpreter’s language with An interpreter repeats the speech.
An event glossary of up to 30 terms, saved songs and special words help with event vocabulary. A new language enters the menu only after its translations pass Espero’s quality tests. Quality is also measured in blind evaluations when the translation model or its instructions change. A correction updates every language.
After the event
Correct the text and download it as TXT, HTML or PDF in every caption language. You can also let listeners download the text from the same link. Text is kept for 30 days from the start of the broadcast.
Use as demo recording turns a finished broadcast into a demo recording with its own link and QR code. It plays around the clock on the real viewing page, with captions and a prepared AI voice in up to 10 of the broadcast’s languages. Anyone can try it without an account.
When the event ends, the viewing page invites listeners to continue in the event’s group conversation.
Where it is used
Use Espero for churches, schools, football events, conferences, associations and training sessions. See the event captions page for the organizer workflow.
Follow a church service from preparation to follow-up, or plan a day with the conference translation guide.
Pricing
Captions in the spoken language are included with translations. Each translation and each listening language has one rate. Annual: €2.50/h + VAT. Monthly: €3.00/h + VAT. One-off: €3.30/h + VAT. Spoken-language captions alone cost one language.
Try 7 hours free, with no card needed and time usable in parts. A broadcast funded only by trial hours holds up to three languages, the spoken one included, with AI-voice listening in one of them.
Time is used while the microphone is on. After two minutes without speech, the meter pauses. Speech starts the meter again. A paused microphone uses no time. Example: a 1.5-hour event in Finnish. English captions cost €3.75 + VAT annually. With English listening: €7.50 + VAT. If you have bought hours before, broadcasting can continue. This applies when your broadcast exhausts the balance. The limit is one extra hour. We deduct that time from your next purchase.
Buy organizer hours by card in Espero. See packages and prices, or request an organization quote.
Try it
Try the interactive event demo, or scan this QR code to open the same demo on your phone. At a real event, guests scan the event’s own QR code.
Frequently asked questions
What is AI live interpretation?
For events, Espero provides AI live interpretation: the speaker talks in their own language, and each guest reads live captions or listens to an AI voice in their own language on their own phone, joining by QR code or link with no app or account.
Do guests need an app or an account?
No. Guests open the event’s QR code or viewing link in their browser and choose their language. Reading captions and listening to the translation need no app or account. The event’s group conversation needs a free Espero account; an email address is enough.
How many languages and listeners can an event have?
Choose from a 106-language catalog, with up to 10 languages per broadcast, the spoken language included. Up to 400 listeners per event are included. Organizations can request an annual agreement for larger events. North Sami is caption-only.
What equipment do we need?
One phone is enough to run the captions. You can also use a mixer over USB or Dante, or a computer audio source. Guests follow on their own phones or computers and can use headphones to listen.
Can we use a venue screen and a livestream?
Yes. Projector view shows large captions on the venue screen. Stream caption overlay adds a transparent caption page per language to OBS, vMix or ProPresenter. The link for stream viewers lets guests read and listen in time with the stream.
Can Espero work alongside a human interpreter?
Yes. Keep your human interpreters in the event and add Espero for audience languages they do not cover. Add the interpreter’s language with An interpreter repeats the speech.
What does live translation cost?
Example: a 1.5-hour event in Finnish. English captions cost €3.75 + VAT annually. With English listening: €7.50 + VAT. Captions in the spoken language are included with translations. Each translation and each listening language has one rate. Annual: €2.50/h + VAT. Monthly: €3.00/h + VAT. One-off: €3.30/h + VAT. Spoken-language captions alone cost one language. Time is used while the microphone is on. After two minutes without speech, the meter pauses. Speech starts the meter again. A paused microphone uses no time.
Can we get the text afterwards?
Yes. The organizer can correct and download the text as TXT, HTML or PDF in every caption language, and can let listeners download it from the same link. Text is kept for 30 days from the start of the broadcast.
How is our data protected?
Messages are encrypted in transit and at rest, and the primary database is in the EU (Ireland). Espero uses the paid APIs of AI services whose terms state that the providers do not use the content to train their own models; they may keep requests for a limited period for abuse monitoring. Security and privacy lists where each service provider processes data and how long it is kept.
How can we try it?
Open the interactive demo, or start a 7-hour free trial with no card. Trial time can be used in parts. A trial-only broadcast holds up to three languages, the spoken one included, with AI voice in one of them.
About Espero
Espero is an AI-powered multilingual messaging app that automatically translates text, voice messages, images and video into each recipient's own language.
For events, Espero provides AI live interpretation: the speaker talks in their own language, and each guest reads live captions or listens to an AI voice in their own language on their own phone, joining by QR code or link with no app or account.