Speechy
Enable high quality Speech to text in 20+ languages, support files up to 1 hours long. Different audio sources require different adaptations, for instance, live recordings (e.g. school or uni) may contain a lot of noise, compared to a crisp youtube podcast by Lex Fridman. We have different endpoints for each type. Choose wisely. Furthermore, you can convert any youtube video to text (personal…
Speechy endpoints
| Method | Endpoint | Description |
|---|---|---|
| POST |
Convert Video/Audio To Text [FASTER] /media-to-text-faster |
Convert any audio or video file to text. It uses a lighter model, so it is faster. Use this when: - audio is crisp - you want faster responses |
| POST |
Convert Video/Audio To Text [ACCURATE] /media-to-text-accurate |
Convert any audio or video file to text with our most accurate model. Response time benchmarks: - 5min audio -> 20 seconds - 20min audio -> 2.5 minutes |
Speechy pricing
| Plan | Price | Rate limit | Quotas |
|---|---|---|---|
| BASIC | Free | — |
|
| PRO | Free | 1 / minute |
|
| ULTRA Recommended | $3.99 / month | 1 / minute |
|
| MEGA | $5.99 / month | 1 / minute |
|