Speech-to-Text AI
OpenAI Whisper real-time speech recognition for audio/video files and YouTube videos. Supports mp3, mp4, mpeg, mpga, m4a, wav and webm. Converts audio to text with support for multiple languages, ensuring precision and reliability.
Speech-to-Text AI endpoints
| Method | Endpoint | Description |
|---|---|---|
| Queue | ||
| POST |
Add transcription to queue /queue |
Adds a request to the queue to transcribe YouTube videos, files from remote URLs or local uploads, supporting formats like mp3, mp4, mpeg, mpga, m4a, wav, or webm. |
| GET |
Get the transcription status /queue/{requestId}/status |
This endpoint allows you to get the status of a queued transcription process. The request ID is required to identify the specific transcription process. |
| GET |
Get transcription result /queue/{requestId}/result |
This endpoint allows you to get the result of a queued transcription process. The request ID is required to identify the specific transcription process. The result will include… |
| Other endpoints | ||
| POST |
Transcribe text /transcribe |
Transcribe or translate mp3, mp4, mpeg, mpga, m4a, wav or webm files from remote URL or uploaded file (up to 100MB). |
| GET |
Transcribe from url /transcribe |
Transcribes YouTube, TikTok, Instagram, Facebook, X (Twitter), Vimeo or LinkedIn videos or files from remote URLs, supporting formats like mp3, mp4, mpeg, mpga, m4a, wav, or webm. |
| GET |
Transcribe text /transcribe |
Transcribe or translate mp3, mp4, mpeg, mpga, m4a, wav or webm files. |
| POST |
Transcribe from url or file /transcribe |
Transcribes YouTube videos, files from remote URLs or local uploads, supporting formats like mp3, mp4, mpeg, mpga, m4a, wav, or webm. |
Speech-to-Text AI pricing
| Plan | Price | Rate limit | Quotas |
|---|---|---|---|
| BASIC | Free | — |
|
| PRO Recommended | $10 / month | — |
|
| ULTRA | $50 / month | — |
|
| MEGA | $100 / month | — |
|