Live captions and translation
Transcribes and translates live speech across a catalogue of 58 languages, with automatic source-language detection and support for switching languages during a talk.
SCAPTION
SCAPTION provides real-time captions and AI translation for conferences, ceremonies, corporate events, and hybrid productions. Attendees access captions and participation tools on their phones by QR code, while organisers can send caption graphics to NDI, HDMI, or browser-based screens.
Live captions and translation for events
SCAPTION is live captioning and AI translation software for conferences, public ceremonies, corporate events, and other spoken-word programmes. It receives audio on a Windows or Mac computer and produces translated captions in roughly two seconds for venue screens, attendee phones, and professional video workflows.
Attendees join by scanning a QR code and selecting a language; no app installation, login, or per-attendee charge is required. Organisers can also use the same event room for moderated questions, audience voting, transcript export, and—on applicable plans—an AI-generated event summary.
Key features
Broadcast-ready outputs
Delivers a 1080p NDI feed with true alpha transparency, full-screen HDMI output with chroma key, or a browser-based caption screen for a TV. It can connect to production tools including OBS Studio, vMix and TriCaster.
Phone access without installation
Lets attendees scan a QR code, select a language, and read or listen on their phones without an app or login. Up to 12 target languages can be selected at once on attendee phones.
Moderated participation
Provides moderated audience questions and live polls. Attendees can submit and upvote questions or vote in their language, while the moderator chooses what to launch on screen.
Flexible audio and multi-mic input
Accepts audio from ASIO and WDM devices, USB microphones, a sound desk, the computer itself, and online meeting applications such as Zoom, Teams, Meet and Webex. Plans support between one and four simultaneous microphones.
Event workflow tools
Includes custom vocabulary, caption styling, transcript export in TXT, SRT and VTT formats, and an AI event summary on paid plans that include it.
Use cases
Multilingual conferences
Display original or translated captions on an auditorium screen while also giving attendees a phone-based way to follow the programme in a selected language.
Broadcast and streamed productions
Feed transparent captions into a vision mixer or use HDMI chroma key for a clean programme output alongside cameras, presentation slides, and other live graphics.
Interactive public meetings
Run moderated questions and polls from a tablet while attendees submit, upvote, and vote from their phones. The moderator controls which item reaches the room screen.
Multi-room events
Reserve separate room codes for plenary sessions and workshops so attendees can select the room they are attending, with room-specific questions, votes, and summaries.
Hybrid and online sessions
Connect audio from a sound desk, USB microphone, or meeting application to provide captions for an in-person, online, or hybrid session.
Pros and Cons
Pros
- Supports live transcription and translation across 58 languages, with automatic source detection.
- Attendees can read or listen on their own phones through a QR code without installing an app or signing up.
- Provides production outputs including transparent NDI, chroma-key HDMI, and a browser-based screen.
- Combines captions with moderated audience questions, polls, and event workflow tools.
- Offers a free one-hour trial with no expiry and no card requirement.
Cons
- The local caption engine and NDI output still rely on an internet connection to relay audio and text; the attendee output fades if the connection drops.
- Some capabilities vary by plan, including translation, reserved room codes, AI summaries, microphone count, and whether the trial stops when its included hour is used.
- The free trial places a small SCAPTION watermark on the programme output.
FAQ
What equipment and audio sources does SCAPTION support?
SCAPTION runs on Windows or Mac. Audio can come from a sound desk, USB microphone, the computer’s own audio, or conferencing software such as Zoom, Teams, Meet and Webex. The product supports ASIO and WDM audio input.
What outputs can SCAPTION provide?
SCAPTION can provide a 1080p NDI source with true alpha transparency for compositing in a switcher. It also offers full-screen HDMI output with chroma key, and a browser-based caption screen for TVs that do not use NDI.
How quickly do captions appear?
Captions reach the venue screen in about 1.7 seconds, with a stated latency of under 2.5 seconds at the 95th percentile. Translation-off captioning is described as taking about 0.7 seconds from audio input to output.
What does the free trial include?
The free trial provides one hour of the full captioning and translation product, with no expiry and no card required. The trial supports one microphone and one session of up to one hour, and includes a small watermark on the programme output.
How do attendees access captions and audience participation?
Attendees scan a QR code, choose a language, and read or listen on their phones without installing an app or creating an account. Organisers can also enable moderated questions and polls, with the moderator deciding what appears on the venue screen.
Quick Facts
- Category
- Live captioning and AI event translation
- Platforms
- Windows and Mac
- Languages
- 58 transcription and translation languages
- Audience access
- QR code in a mobile browser; no app or login
- Production outputs
- 1080p NDI with alpha, chroma-key HDMI, or browser screen
- Primary users
- Conference, ceremony, corporate-event, and live-production organisers
SCAPTION Alternatives
Pewbeam
Pewbeam is a church presentation app that listens to sermons, detects Bible verse references in real time, and displays the matching passage on screen for smoother live services.
CAMB.AI Streams
CAMB.AI Streams dubs live audio in real time for YouTube, Twitch, X and other platforms, using existing live workflows and no post-production.
Tavus
Tavus is an AI video platform for real-time face-to-face agents, digital twins, and AI companions, with APIs and multilingual workflows for developers.
SpeakoFlow
SpeakoFlow is a free, open-source desktop voice-to-text app for Windows, macOS, and Linux. Dictate into any app, use Flow, cleanup, translation, and a screen-aware assistant.
Sanota
Sanota turns spoken memories and interviews into clear written stories for personal storytelling, family history and shared memories, with guided prompts and subscriptions.
Carbon Voice
Carbon Voice is an async voice messaging app for teams and individuals, with transcripts, AI catch-up, and cross-device access.