Audio & Video Transcriber — Speech to Text API
Pricing
from $9.00 / 1,000 audio minutes
Audio & Video Transcriber — Speech to Text API
Convert speech to text from any public audio or video URL: podcast episodes, MP3, WAV, M4A or MP4 files and video pages on other sites. Get timestamps, SRT/VTT subtitles, speaker labels and RAG-ready JSONL with source times. Up to 4 hours per file and 1,000 URLs per run. No speech API key needed.