Open AI Whisper transcribe speech to text
OpenAI Whisper is a powerful, multilingual speech-to-text model that accurately transcribes audio across various languages and accents. Leveraging advanced deep learning techniques, it can handle diverse audio inputs, making it ideal for applications in transcription, translation, and voice-based interactions
38 subscribers
8.9/10 popularity
546 ms avg latency
80% success rate
2 endpoints
The in-depth APIMemo review for this API hasn't been published yet —
the data below comes straight from the public marketplace listing.
Open AI Whisper transcribe speech to text endpoints
| Method | Endpoint | Description |
|---|---|---|
| POST |
Transcribe to text /whisper |
Make an API call to Transcribe to convert audio to text, which returns a **result ID** that you'll use to poll the **Results **endpoint with the **result ID**. |
| GET |
Result /whisper |
Check job status and result |
Open AI Whisper transcribe speech to text pricing
| Plan | Price | Rate limit | Quotas |
|---|---|---|---|
| BASIC | Free | — |
|
| PRO | $20 / month | — |
|
| ULTRA Recommended | $50 / month | — |
|
| MEGA | $100 / month | — |
|
