AI Services

AI Services are a suite of intelligence APIs for common AI workloads. You can use these APIs to access flexible AI-powered features that process media data and create customized solutions.

Scribe API

Scribe API: Speech-to-text transcription for audio. It supports fast, synchronous transcription and large-scale batch processing.

This API enables:

  • Faster processing

    Transcribes up to 1,000 audio files in a single job.

  • Smart formatting

    Automatically adds timestamps, punctuation, and speaker separation.

  • Language support

    Starts with English transcription, with additional languages coming soon.

  • Common audio formats

    Transcribes WAV, M4A, MP3, and MP4 files.

Coming soon

AI Services with additional capabilities across speech, vision, and text in future releases.