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 provides 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

• Common audio formats

  Transcribes WAV, M4A, MP3, and MP4 files

Summarizer API

Summarizer API offers conversation and meeting summarization for transcripts from any system. It supports fast synchronous summarization and large-scale batch processing.

This API enables:

• Conversation-focused summarization

  Summarizes meeting, call, chat, and other dialogue-based transcript content

• Structured outputs

  Returns recap, action item, summary, or full summary results for workflows and automation

• Flexible processing

  Supports inline text requests and storage-based batch jobs for transcript files

Translator API

Translator API delivers machine translation for text across a broad range of languages. It supports fast synchronous translation and large-scale batch processing.

This API enables:

• Fast translation

  Translates plain text in a single synchronous API call

• Batch processing

  Processes multiple files asynchronously for large-scale translation workloads

• Broad language support

  Translates across 9 supported languages

Coming soon

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