Built by Metorial, the integration platform for agentic AI.
Provider Summary
transcribe audio files
real-time speech-to-text
speaker diarization
translate transcripts
generate summaries
sentiment analysis
named entity recognition
generate subtitles
extract structured data
custom prompt responses
Transcribe audio and video URLs with asynchronous or real-time speech recognition. Discover transcription jobs, retrieve transcripts and audio intelligence, and delete pre-recorded or live results. Configure speaker diarization, translation, summaries, sentiment, entities, custom vocabulary, spelling corrections, and transcript prompts. Receive generated SRT/VTT subtitles as downloadable files. Live sessions return a WebSocket URL for an external audio-streaming client.
This integration is licensed under the FSL-1.1.
Built with ❤️ by Metorial