Voice Analysis
Base URL: https://app.lisn.dev/api
Send an audio file for processing. The system will transcribe the audio using the configured STT provider, then analyze the transcript with the LLM.
Endpoint
| Method | Endpoint | Description |
|---|---|---|
POST | /api/v1/requests/voice | Process audio file |
Parameters (multipart/form-data)
| Field | Type | Required | Description |
|---|---|---|---|
assistant_id | string | Yes | ID of the assistant to use |
audio_file | file | Yes | Audio file (.mp3, .wav, .m4a, .ogg, .webm) |
cURL Example
curl -X POST "https://app.lisn.dev/api/v1/requests/voice" \
-H "Authorization: Bearer YOUR_API_TOKEN" \
-F "assistant_id=ast_abc123" \
-F "audio_file=@recording.wav"Python Example
import requests
response = requests.post(
"https://app.lisn.dev/api/v1/requests/voice",
headers={"Authorization": "Bearer YOUR_API_TOKEN"},
data={"assistant_id": "ast_abc123"},
files={"audio_file": open("recording.wav", "rb")},
)
print(response.json())Supported Audio Formats
| Format | Extension |
|---|---|
| MP3 | .mp3 |
| WAV | .wav |
| M4A | .m4a |
| MP4 | .mp4 |
| OGG | .ogg |
| WebM | .webm |
See Response Format for the full session object returned after processing.