Speech to Text with OpenAI Whisper
Trusted by members of many leading organizations and universities.
Frequently asked questions
Is this app free?
Whisperui.com is free to use with some basic features. You will need to have a working OpenAI API Key for you to use the app. By using the API Key you will pay directly to OpenAI for the amount of tokens you use.
What are the premium features?
The premium features include: Upload multiple files at once. Unlimited daily files upload. Transform audio files into SRT files.
How do i get an OpenAI API Key?
You can get your API key directly with OpenAI at https://platform.openai.com/account/api-keys
Is my API key safe?
Your API is safe and stored locally on your browser.
What can i do with WhisperUI?
You can transform audio files into text and SRT files by using OpenAI Whisper Speech to Text.
What is OpenAI Whisper?
Whisper is an ASR system that has been trained on a vast and varied dataset comprising 680,000 hours of multilingual and multitask supervised data sourced from the internet. The application of such an extensive and diverse collection of data has resulted in the system displaying superior robustness in the face of accents, background noise, and technical language. Additionally, the system is capable of transcribing speech in multiple languages and translating them into English.
How does the audio-to-text transformation process work?
The user uploads an audio file to our web app, which then uses OpenAI Whisper to transcribe the spoken words into text. The resulting text is displayed to the user for editing and correction.
What types of audio files are compatible with WhisperUI?
WhisperUI supports MP3, MP4, MPEG, MPGA, M4A, WAV, OGG and WEBM.
What is the maximum allowed file size?
OpenAI limits the file upload to 25MB. If your file exceeds the 25MB limit you can compress your file for free here.
How accurate is the transcription process?
OpenAI Whisper is known for its high accuracy, but the final transcription will depend on the quality of the audio file and the clarity of the spoken words.
How long does it take to transcribe an audio file?
The time it takes to transcribe an audio file depends on its length and the complexity of the spoken words. However, most files are transcribed within a few minutes.
What are the supported languages?
OpenAI Whisper supports several languages including English, Spanish, French, German, Chinese, and more.
OpenAI Quota Exceeded Message: What Does It Mean?
This message usually appears when your OpenAI account doesn't have enough credits or if credits were recently added. In some cases, it can take up to 6 hours for OpenAI to enable your credits.