Use cases

Every product below runs on the same thing: recorded audio turned into a transcript that knows who said what, and when. About 60,000 hours of audio a month go through the API in production.

• Podcast transcription API with speaker labels

  Transcribe podcast episodes with host and guest labelled, word-level timestamps for clips and chapters, and SRT/VTT captions. Batch API, $0.18 an audio hour with diarization included.

• Meeting transcription API: who said what, with timestamps

  Transcribe recorded meetings with each speaker separated, word timestamps and automatic language detection, for notetakers and meeting assistants. $0.18 an audio hour, diarization included.

• Call recording transcription API for QA and conversation intelligence

  Transcribe recorded sales and support calls with agent and customer separated, word timestamps and automatic language detection, for call QA and conversation intelligence. $0.18 an audio hour.

• Interview transcription API for user research and qualitative analysis

  Transcribe user interviews, focus groups and research sessions with interviewer and participants separated and timestamps for every quote. Batch API, $0.18 an audio hour.

• Subtitle generation API: SRT and VTT from any audio or video

  Generate SRT and VTT subtitles from audio and video with accurate word timing, automatic language detection and speaker changes. One API call, $0.18 an audio hour.