API reference
Speech Translate
Translate Odia audio into English text.
POSThttps://api.langgenie.ai/v1/speech-translate
Headers
| Field | Type | Required | Description |
|---|---|---|---|
| api-subscription-key | string | Yes | Your API key. |
Body · multipart/form-data
| Field | Type | Required | Description |
|---|---|---|---|
| file | binary | Yes | Audio file. WAV, MP3, M4A, OGG/Opus, FLAC or WebM. Max 25 MB. |
| model | string | No | Model ID. Defaults to "langgenie-od-en-v1". |
| with_timestamps | boolean | No | Return segment-level start/end times. Default false. |
Example
import requests
# Odia speech → English text
response = requests.post(
"https://api.langgenie.ai/v1/speech-translate",
headers={"api-subscription-key": "YOUR_API_KEY"},
files={"file": open("sample.wav", "rb")},
data={"model": "langgenie-od-en-v1", "with_timestamps": "true"},
)
print(response.json()["transcript"])Response
200 OK
{
"request_id": "req_8f2c1e9a4b7d3a10",
"model": "langgenie-od-en-v1",
"transcript": "Hello, today I would like to know about the land record of my plot.",
"source_language": "od-IN",
"target_language": "en-IN",
"duration_seconds": 4.2,
"segments": [
{
"start": 0,
"end": 4.2,
"text": "…"
}
]
}