New: Multi-Lingual Voiceover for Live Captions and CART
Live captions and real-time translation already remove barriers for attendees who are deaf or hard of hearing, and for those who speak a different language. But what about attendees who would benefit from hearing the translation rather than reading it? Starting today, Recap Innovations supports multi-lingual voiceover for translated live captions, powered by high-quality natural sounding text-to-speech.
What is multi-lingual voiceover?
When an audience member opens the live caption viewer and selects a translation language, they can now enable voiceover with a single click. Each translated caption is synthesized into realistic human-sounding speech on our servers and streamed back as audio to the listener's device. There is nothing to install, no browser compatibility concerns, and voice quality is consistent across every device and platform.
Voiceover works alongside all three of our live captioning service tiers: fully automated AI, AI with human editing, and professional CART.
High-quality, natural-sounding voices
Our voiceover engine selects the best available voice for each language, preferring the highest quality tier for the most natural sounds. This means listeners hear clear, expressive speech regardless of what device or browser they use, and without having to put up with voices that sound very robotic or are hard to listen to. The same voice quality is available whether an attendee is on a laptop, a phone, or a tablet.
Audio is synthesized on demand and cached so that repeated cues play back instantly without additional processing time.
Two playback modes
Every user's listening preference is different, so we built two voiceover modes:
- Automatic: Translated captions are spoken sequentially as they arrive. Each cue plays to completion before the next begins, so listeners never hear a sentence cut off mid-word. If the voiceover falls behind the live stream, the system suggests increasing the playback speed.
- On-demand: A small play button appears beside each translated caption. The listener chooses which cues to hear, and can replay them as many times as they like. This is ideal for attendees who want to read most captions but occasionally hear a specific passage spoken aloud.
Users switch between modes in the caption and voiceover settings dialog.
Visual speaking indicator
In automatic mode, a subtle animated indicator appears next to the caption cue currently being spoken. This helps the listener follow along in the transcript, especially when the voiceover is a few cues behind the latest caption.
How moderator edits interact with voiceover
For our AI with human editing and professional CART tiers, moderators can correct caption text in real time. When a moderator edits a caption that is already queued for voiceover but has not yet started speaking, the voiceover automatically picks up the corrected text. If the cue is already being spoken, the correction takes effect visually but does not interrupt the audio, since cutting off mid-sentence would be a worse listening experience.
Settings discoverability
First-time users told us the voiceover toggle button was easy to find, but it was not obvious that speed and volume controls lived inside the settings dialog. When voiceover is enabled, the settings button now reads "Caption and voiceover settings" to make that connection clear.
Getting started
Multi-lingual voiceover is available now on all Recap Innovations live caption viewer links. No configuration changes are needed by event organizers or administrators. Attendees simply:
- Open the live caption link on their device
- Select a translation language
- Click the voiceover button
- Optionally open settings to adjust speed or switch to on-demand mode
Language coverage
Because voiceover is powered by server-side synthesis rather than the listener's browser, it works for every translation and voiceover language pair we support. There is no dependency on what voices a particular device or browser happens to have installed.
Multi-lingual voiceover is one more step toward making live events accessible to every attendee, regardless of hearing ability or language. If you have questions or feedback, reach out to sales@recap-innovations.com or schedule a demo.