Speech to Text & Audio Transcription: $0.0025/min, No Login
Pricing
from $2.50 / 1,000 audio minute (english, standard)s
$0.0025 per audio minute in English. Transcribe audio and video files and podcast RSS episodes to text with timestamps and SRT or VTT subtitles. High-accuracy English $0.003 and about 100 other languages $0.01 per minute. No API key or login. Failed or silent files are free.
Enter direct links to audio or video files, one per line: MP3, M4A, AAC, WAV, FLAC, OGG, OPUS, MP4, MOV, WEBM or MKV. Use your own files or a podcast episode's file link.
[ "https://raw.githubusercontent.com/openai/whisper/main/tests/jfk.flac"]Enter podcast RSS feed links, one per line. The newest episodes of each feed are transcribed (see Episodes per feed).
[ "https://example.com/podcast/feed.xml"]Transcribe this many of the newest episodes from each podcast RSS feed.
Transcribe at most this many files in this run, file links first, then feed episodes. Duplicates count once.
Choose the spoken language. English uses the English models. Any other choice, or Detect automatically, uses the multilingual model (about 100 languages), which costs more per minute.
Standard is the lowest price. High uses a larger English model with fewer errors and costs more per minute. Applies when Language is English.
Save these subtitle files for each transcript in the key-value store. Each dataset row links to them.
[ "srt"]Add the segments list (start, end, text) to each dataset row.
Transcribe at most the first this many minutes of each file. You pay only for the minutes transcribed.