OpenAI Whisper AI (Transcription)

This is a client-side page that uses the OpenAI Whisper API to generate text from speech.

You need to insert your own API key for it to function (and so you pay for whatever you use directly to OpenAI). Go to OpenAI API Keys page to get your key.

The audio data is uploaded directly to OpenAI. They impose a limit of 25MB as of the time of writing this.

For pricing, see OpenAI Pricing (scroll down or search for Whisper). For more API details, see API Documentation.

API Key

Audio file

Audio language (optional) - The language of the input audio. Supplying the input language in ISO-639-1 format will improve accuracy and latency.

Prompt (optional) - An optional text to guide the model's style or continue a previous audio segment. The prompt should match the audio language.

Response format - The format of the output.

The timestamp granularities to populate for this transcription. response_format must be set verbose_json to use timestamp granularities. Either or both of these options are supported: word, or segment. Note: There is no additional latency for segment timestamps, but generating word timestamps incurs additional latency.

Temperature - The sampling temperature, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. If set to 0, the model will use log probability to automatically increase the temperature until certain thresholds are hit.