Speech to text

import os
from openai import OpenAI

client = OpenAI(base_url="https://api.naga.ac/v1", api_key=os.environ["NAGA_API_KEY"])

with open("speech.mp3", "rb") as audio:
    transcript = client.audio.transcriptions.create(
        model="gpt-4o-transcribe",
        file=audio,
        language="en",
    )

print(transcript.text)

import fs from "node:fs";
import OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.naga.ac/v1", apiKey: process.env.NAGA_API_KEY });

const transcript = await client.audio.transcriptions.create({
  model: "gpt-4o-transcribe",
  file: fs.createReadStream("speech.mp3"),
  language: "en",
});

console.log(transcript.text);

curl https://api.naga.ac/v1/audio/transcriptions \
  -H "Authorization: Bearer $NAGA_API_KEY" \
  -F model=gpt-4o-transcribe \
  -F file=@speech.mp3 \
  -F language=en

import os
from openai import OpenAI

client = OpenAI(base_url="https://api.naga.ac/v1", api_key=os.environ["NAGA_API_KEY"])

with open("question.mp3", "rb") as audio:
    translation = client.audio.translations.create(
        model="whisper-large-v3",
        file=audio,
    )

print(translation.text)

import fs from "node:fs";
import OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.naga.ac/v1", apiKey: process.env.NAGA_API_KEY });

const translation = await client.audio.translations.create({
  model: "whisper-large-v3",
  file: fs.createReadStream("question.mp3"),
});

console.log(translation.text);

curl https://api.naga.ac/v1/audio/translations \
  -H "Authorization: Bearer $NAGA_API_KEY" \
  -F model=whisper-large-v3 \
  -F file=@question.mp3