Knowledge base · audio
Whisper
Speech-to-text transcription: upload audio, get a text transcript. Handy for subtitles, notes and interviews.
Open in studio →What it can do
- ✓Recognizes speech from an audio file and returns text.
- ✓Understands many languages.
- ✓Suits subtitles, interview transcription and voice messages.
How to write a prompt
No prompt is needed, just attach an audio file. The cleaner the recording (less noise, one speaker), the more accurate the text.
A prompt that works
(attach an audio file), the transcript comes back automatically
Avoid this
“voice this text”
Whisper does the opposite, it turns speech into text. To voice text, choose ElevenLabs.
Examples
Subtitles for a video
(attach the audio from a video), you get text for subtitles
Tips
- →One speaker and a quiet background → noticeably more accurate.
- →Split a long interview into chunks of 5 or 10 minutes.
FAQ
How much does a generation in Whisper cost?
6 tokens per generation, depending on the chosen version and settings. Current plans and token packs are on the /en/pricing page.
Can the results of Whisper be used commercially?
Yes, with an active Pixyn subscription. Note that some models have provider restrictions by industry, check the terms of the specific version.