AI speech recognition API with transcription, speaker diarization, sentiment analysis, and audio intelligence.
No notes have been added for this tool yet.
Turn on speaker_labels when transcribing multi-person audio — diarization is a config flag, not automatic, and skipping it merges everyone into one speaker.
Use the auto_chapters or summarization params to get structured output directly from the API instead of post-processing the raw transcript yourself.
For domain-specific terms (product names, jargon), pass a word_boost list — it meaningfully improves recognition accuracy outside general English vocabulary.
No reviews yet. Be the first!