.webp?width=468&quality=high)
Make sure even hard-to-catch but crucial words like unique names, technical terms, and abbreviations are not missed by AI. We use best-in-class speech-to-text technology and customize the engine to the terminology of your event.
Bring world-class AI live captioning to your audiences in Teams, Zoom, or even your auditorium to make your meetings more accessible.
As a visual aid to follow the speech, live audio is transcribed into text through AI-powered Automated Speech Recognition (ASR), or often also referred to as "speech-to-text" technology.
Interprefy Captions are generated off the audio speech of each speaker (and interpreter, if active) using Automated Speech Recognition (ASR) technology powered by Artificial Intelligence (AI).
This technology combination uses speech-to-text processing technology to provide text directly from the words being spoken. Just like interpretation, captions will follow as live transcription slightly after the speaker has delivered their words.
In the diagram below, you can see how ASR works, when you have an English speaker, and a Spanish interpreter connected:
We only support languages that have been tested thoroughly in collaboration with a linguistic partner and meet rigorous quality standards. Our system uses human-curated custom glossaries to add a layer of human refinement to raw ASR output, leading to better accuracy for you and your audience. Audio input factors such as heavy accents or low audio quality can impact captioning accuracy.
Custom glossaries are lists of terms and phrases specific to your sessions, that our project team uses to guide an ASR engine, so it produces the words correctly when it ‘hears’ them. After collecting and compiling key names and terms, professional linguists use their in-depth language knowledge to program phonetic pronunciations into the system. This process makes the automatic live captions more accurate.
Interprefy Captions have a similar or even shorter time delay than human-generated live captions. The delay between the audio and the Interprefy Captions is usually around two to four seconds, depending on the preferred setting, whereas human-generated captions are usually delayed by around four to seven seconds.
Interprefy Captions can be enabled in two different modes. By default, the text will appear within 4 seconds of the speaker having completed a sentence. If 'instant mode' is activated, the text will appear in real-time with rapid auto-correction.
We are a language technology company with a strong belief that humans and machines working together lead to outstanding results. We use best-of-breed ASR technology and continuously benchmark existing and new ASR systems to offer customers solutions that are best suited for their needs. Our system utilizes linguistic expertise to improve these engines and guide them to capture customer-specific terms and phrases that are typically difficult to capture.
What's more, we provide end-to-end services to support you at every step of the way. To make sure the process and delivery are as smooth as possible.
Absolutely. We can deliver simultaneous interpretation alongside live captions, and also turn audio interpretation into text for your audience to follow.
We can automatically recognize and transcribe speech in over 30 languages. Click here for the latest list of supported languages.
Download from the App Store
Download from Google Play
More download links
