Whisper - Speech To Text
Whisper is a general-purpose speech recognition model. It is trained on a large dataset of diverse audio and is also a multitasking model that can perform multilingual speech recognition, speech translation, and language identification.
6 subscribers
8.6/10 popularity
4179 ms avg latency
76% success rate
1 endpoints
The in-depth APIMemo review for this API hasn't been published yet —
the data below comes straight from the public marketplace listing.
Whisper - Speech To Text endpoints
| Method | Endpoint | Description |
|---|---|---|
| POST |
Speech To Text /api/v1/whisper |
Transcribe an audio file into text using OpenAI’s Whisper model. Accepts a binary audio payload as multipart/form-data. |
Whisper - Speech To Text pricing
| Plan | Price | Rate limit | Quotas |
|---|---|---|---|
| BASIC | Free | 10 / hour |
|
| PRO | $4.99 / month | 1 / second |
|
| ULTRA Recommended | $29.99 / month | 1 / second |
|
| MEGA | $99.99 / month | 1 / second |
|
