Speech Recognition API
A Speech Recognition API is an interface that enables developers to integrate voice-to-text functionality into applications or services. It converts spoken language into textual form using audio processing and language modeling techniques. Core Features: Real-time transcription: Instantly converts spoken audio into text. Language support: Typically supports multiple languages and dialects.…
Speech Recognition API endpoints
| Method | Endpoint | Description |
|---|---|---|
| Endpoints | ||
| POST |
asr_asr_post /asr |
Convert audio files to text with high accuracy. Supports multiple languages and output formats. |
| POST |
detect_language_detect_language_post /detect-language |
Automatically identify the primary language spoken in an audio file |
Speech Recognition API pricing
| Plan | Price | Rate limit | Quotas |
|---|---|---|---|
| BASIC | Free | — |
|
| PRO | $4.99 / month | 100 / hour |
|
| ULTRA | $9.99 / month | 1000 / hour |
|
| MEGA Recommended | $19.99 / month | 10000 / hour |
|