Menu
Build, scale, and operate a world-class engine.
New accuracy updates launch every 6 weeks.
Our API is built using the latest advances in Deep Learning, using cutting edge research from our in-house team of AI researchers.
Don't worry about file formats or sampling rates, our API supports virtually all audio/video files accurately without any transcoding required.
Boost accuracy for key terms and phrases like person or product names, places, and other vocabulary unique to your application.
Easily export your transcription in SRT or VTT format, to be plugged into a video player for subtitles and closed captions.
Casing and punctuation of proper nouns are automatically added to the transcription text, to make transcripts produced by the API more readable.
The API can automatically detect key phrases and words in your transcription text - very useful for tagging content, and providing a summary of the transcription text.
Select a customized model for Australian, UK, South African, and more dialects to boost accuracy on your data.
Phone calls recorded in stereo/dual channel are transcribed separately, and you'll get a transcript for each channel.
We always follow best-practice guidelines like encryption in transit and at rest, and are not in the business of monetizing your data. Files sent to the API for transcription are never stored, and you can request the deletion of transcription text permanently from our database.
With a historical uptime and transcription completion rate of 99.9%+, you can feel confident integrating our API into your product.
Request for a transcript to be generated 25-50% faster than normal.
We're here to work with you as much, or as little, as you'd like. Talk to us over live chat, Slack, email, or phone.
Have audio/video files stored in S3, GCP, or on your server? The API can download and transcribe any file accessible via a URL.
Our team can work directly with you to fine-tune our models for your use case and data, in order to boost accuracy.
Upload your audio/video files directly to the API for transcription.
Receive webhooks from our API as soon as your transcriptions are finished processing.
Replace PII like social security and credit card numbers with "#" for audio data that has sensitive information.
Word-by-word timestamps across the entire transcript text.
Get a confidence score i.e. .96 for each word in the transcript.
Begin testing in under 2 minutes