OpenAI Whisper API

OpenAI's Whisper API delivers highly accurate, multilingual speech-to-text transcription and translation using the `whisper-1` model.

The OpenAI Whisper API (via the `/v1/audio/transcriptions` endpoint) provides a robust, high-performance speech-to-text solution. It leverages the powerful `whisper-1` model and newer models like `gpt-4o-transcribe` to handle transcription for various audio formats (MP3, WAV, M4A) and multiple languages. Developers also use the translations endpoint to transcribe non-English audio directly into English text. Pricing is efficient, starting at $0.006 per minute for the `whisper-1` model, ensuring cost-effective, high-accuracy integration for applications like call center analysis or media processing.

https://platform.openai.com/docs/guides/speech-to-text