AI Video & Audio Transcriptions API
What is the main use case for Whisper API?
Whisper API is great for transcribing video and audio files via an API. You get full control of the transcription process with options to choose model size, language, format and advanced options like beam size, temperature and many more.
What are some unique features of whisper-api.com?
- Ability to choose model size.
- Support for both file uploads and direct urls in the transcription API
- Support for transcriptions via the user dashboard without API
- Generous file limits. Free users get up to 1GB file uploads!
- Unlimited minutes. No cap on how long the files are.
- Robust API for configuration the transcription parameters.
Can a user use Whisper API for free?
Yes we have a free tier where users get up to 5 free transcriptions a day, no credit card required.
What are the pricing plans for WhisperAPI?
WhisperAPI offers three pricing plans:
- Free Plan: 5 free transcriptions per day, up to 1GB per file, and API access.
- Starter Plan: $49/month, 10,000 transcriptions per month, up to 10GB per file, API access, and email support.
- Pro Plan: $79/month, 50,000 transcriptions per month, up to 10GB per file, API access, and email support.
You can start for free and upgrade when more features are needed.
How accurate are WhisperAPI's transcriptions?
WhisperAPI uses OpenAI's Whisper model, which delivers industry-leading 99.8% accuracy across various audio types. Accuracy may be influenced by audio quality, background noise, and accents, but for clear audio in supported languages, it performs excellently.
What languages and file formats does WhisperAPI support?
WhisperAPI supports 98+ languages, including English, Spanish, French, German, Chinese, and Japanese. It handles most common audio and video formats like MP3, WAV, MP4, and M4A, accommodating files up to 10GB in size with a Pro subscription.
