Speech-to-Text

import os

import requests

with open("meeting.mp3", "rb") as audio:
    response = requests.post(
        "https://api.venice.ai/api/v1/audio/transcriptions",
        headers={"Authorization": f"Bearer {os.environ['VENICE_API_KEY']}"},
        files={"file": audio},
        data={
            "model": "nvidia/parakeet-tdt-0.6b-v3",
            "response_format": "json",
        },
    )

response.raise_for_status()
print(response.json()["text"])

import { createReadStream } from "node:fs";
import FormData from "form-data";

const form = new FormData();
form.append("file", createReadStream("meeting.mp3"));
form.append("model", "nvidia/parakeet-tdt-0.6b-v3");
form.append("response_format", "json");

const response = await fetch("https://api.venice.ai/api/v1/audio/transcriptions", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.VENICE_API_KEY}`,
    ...form.getHeaders(),
  },
  body: form,
});

if (!response.ok) {
  throw new Error(await response.text());
}

const transcript = await response.json();
console.log(transcript.text);

curl https://api.venice.ai/api/v1/audio/transcriptions \
  -H "Authorization: Bearer $VENICE_API_KEY" \
  --form file=@meeting.mp3 \
  --form model=nvidia/parakeet-tdt-0.6b-v3 \
  --form response_format=json