Speech-to-Text Service
Convert audio to text with YODI's transcription API.
Endpoint​
POST https://admin.yodi.tg/api/ai/transcribe
Description​
Transcribe an uploaded audio file into text.
Parameters​
Required​
| Parameter | Type | Description |
|---|---|---|
file | file | Audio file to transcribe |
Optional​
| Parameter | Type | Default | Description |
|---|---|---|---|
langCode | string | fra | Backend language hint sent to the transcription service |
Backend support​
The backend guarantees the default fra path and a dedicated Ewe path for ewe / ewe_Latn. Any other langCode value is forwarded to the upstream transcription service and is not guaranteed by YODI itself.
Example Request​
curl -X POST "https://admin.yodi.tg/api/ai/transcribe" \
-H "Authorization: Bearer YOUR_API_KEY" \
-F "file=@audio.mp3" \
-F "langCode=fra"
Example Response​
{
"message": "SUCCESS",
"error": false,
"data": "Bonjour, comment allez-vous ?",
"status": 200
}
Use Cases​
- Podcast transcription
- Call recording transcription
- Lecture recording transcription
- Accessibility features
- Voice command recognition