Whisper Speech to Text — Audio & Video Transcriber
Pricing
from $40.00 / 1,000 result rows
Transcribe audio and video URLs to timestamped text with speaker labels, chapters, keywords and SRT/VTT subtitles in 99 languages.
Direct URLs to audio or video files (mp3, wav, m4a, mp4, ogg, flac, webm, …). Up to 10 files per run, 500 MB per file.
Alternative to the list above — a single direct media URL.
ISO 639-1 code of the spoken language, e.g. "en", "es", "ko". Leave empty to auto-detect (99 languages supported).
Transcribe speech in any language directly into English text.
Add per-word start/end times to every segment (slower, larger rows). Word times are estimated and can drift by a few hundred milliseconds.
Detects the different voices in the recording and labels every transcript segment with SPEAKER_1, SPEAKER_2, … Adds one speaker summary row per detected voice (speaking time, word count, share of speech, sample quote) and [SPEAKER_N] tags in the SRT/VTT/TXT files. Recommended for meetings, interviews and podcasts.
If you know how many people speak (e.g. 2 for an interview), set it here for more reliable labels. Leave 0 to detect the count automatically.
Adds per-file enrichment rows: one file summary, pause-detected chapters with YouTube-ready timestamps, and the top 10 keywords with every mention's timestamp. Each delivered row is billed like any other result row.
Adds one row per sentence segment (roughly 10 per minute of speech). Useful for pipelines that join on exact timestamps. Off by default because it multiplies the number of billed rows.
Transcription stops after this many minutes of audio per file (cost guard). Longer files are trimmed and flagged with a notice row. Max 240.
