Speech-to-Text Service
Convert audio to text with YODI's speech recognition API.
Endpoint​
POST https://admin.yodi.tg/api/ai/stt
Description​
Transcribe audio files or real-time audio streams into text with high accuracy.
Parameters​
Required​
| Parameter | Type | Description |
|---|---|---|
audio | file | Audio file to transcribe |
Optional​
| Parameter | Type | Default | Description |
|---|---|---|---|
language | string | fr | Language code |
format | string | auto | Audio format: 'mp3', 'wav', 'ogg' |
Supported languages:
mina,ewe,fr,tem
Supported Languages​
| Code | Language |
|---|---|
| mina | Mina |
| ewe | Ewe |
| fr | Français |
| tem | Tem |
Known Limitations​
- Real-time transcription not working
- File upload transcription not working
- Expected availability: Q3 2026
Use Cases​
Once available, this service will support:
- Podcast transcription
- Call recording transcription
- Lecture recording transcription
- Accessibility features
- Voice command recognition