Whisper API Interface

Transcribe your audio files with OpenAI's Whisper model, right from your browser. Interact directly with the API with parameter control and process multiple files at once.

Your browser directly makes requests to OpenAI servers. We don't access or store your files or data.

Authentication

Audio File

Drop audio files here or click to use file picker

Parameters

whisper-1 is the only available model.
The language of the input audio. If not specified, the model will auto-detect the language.
Optional text to guide the output style. Whisper will try to imitate the specific names or acronyms you use. The prompt should be in the same language as the audio.
Controls randomness in the output. Values between 0 and 1. Higher values like 0.8 will make the output more random. The default is 0.
Select verbose_json if you need word-level timestamps.
Only available with verbose_json response format.

Result

API Usage Statistics

Total Requests 0
Successful 0
Failed 0
Average Response Time 0 ms
Total Audio Duration 0 seconds
Estimated Cost $0.0000

About Whisper Transcription

See API documentation

OpenAI's Whisper is a state-of-the-art speech recognition model from OpenAI. The Whisper model supports:

  • Multiple audio formats (MP3, WAV, M4A, and more)
  • Language detection
  • Temperature control for output variation
  • Multiple response formats including SRT and VTT for subtitles
  • Detailed word-level timestamps (in verbose JSON mode)

Looking for an easy way to transcribe audio without writing a single line of code? This browser-based web UI lets you interact directly to OpenAI's Whisper API, providing seamless, high-accuracy speech-to-text transcription for content creators, researchers, podcasters, journalists, and developers.

How It Works

  1. Get an API key — Generate an API key from your OpenAI dashboard

  2. Select your audio files — Drag and drop or click to use your file picker. You can select multiple files to process in a batch.

  3. Get a Transcription — Your files are sent to OpenAI and transcribed using the AI model

  4. Download & Use — Copy or download your transcripts.

Transparent Pricing

OpenAI Whisper’s affordable pricing ensures you pay only for what you use: $0.006 per minute, rounded to the nearest second. Our tool keeps you informed with real-time cost tracking, so there are no surprises.

Who Can Benefit from This Tool?

  • Podcasters & Journalists — Quickly generate interview transcripts.

  • Content Creators — Turn video and audio content into captions or blog posts.

  • Researchers & Academics — Easily analyze spoken data.

  • Developers — Test transcription quality without setting up an entire API workflow.

Privacy & Security

Your files and API key are never seen or processed by us. Your browser sends your data directly to OpenAI. By default, OpenAI does not use the data you send through the API to train or improve their models. API data may be retained for up to 30 days. Read more about their policy