Audio — speech-to-text & text-to-speech

import os, orbitrage
orbitrage.init(os.environ["ORBITRAGE_API_KEY"], user_id="customer_42")

from openai import OpenAI
client = OpenAI()

with open("call.wav", "rb") as f:
    tx = client.audio.transcriptions.create(model="nova-3", file=f)
print(tx.text)

import { orbitrage } from "orbitrage";
await orbitrage.init({ apiKey: process.env.ORBITRAGE_API_KEY, userId: "customer_42" });

import OpenAI from "openai";
import fs from "node:fs";
const client = new OpenAI();

const tx = await client.audio.transcriptions.create({
  model: "nova-3",
  file: fs.createReadStream("call.wav"),
});
console.log(tx.text);

# Raw audio body
curl https://api.orbitrage.ai/v1/audio/transcriptions?model=nova-3 \
  -H "Authorization: Bearer $ORBITRAGE_API_KEY" \
  -H "Content-Type: audio/wav" \
  --data-binary @call.wav

# …or a remote URL
curl https://api.orbitrage.ai/v1/audio/transcriptions?model=nova-3 \
  -H "Authorization: Bearer $ORBITRAGE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"url":"https://dpgr.am/spacewalk.wav"}'

resp = client.audio.speech.create(
    model="aura-2-thalia-en",   # the Deepgram Aura voice
    voice="aura-2-thalia-en",   # the OpenAI SDK requires `voice`; Orbitrage selects the voice from the model id
    input="Hello from Orbitrage. This voice is managed for you.",
    response_format="mp3",
)
resp.stream_to_file("hello.mp3")

const resp = await client.audio.speech.create({
  model: "aura-2-thalia-en",
  voice: "aura-2-thalia-en", // required by the SDK; Orbitrage uses the Aura model id for the voice
  input: "Hello from Orbitrage. This voice is managed for you.",
  response_format: "mp3",
});
const buf = Buffer.from(await resp.arrayBuffer());
await fs.promises.writeFile("hello.mp3", buf);

curl https://api.orbitrage.ai/v1/audio/speech?model=aura-2-thalia-en \
  -H "Authorization: Bearer $ORBITRAGE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"input":"Hello from Orbitrage."}' \
  --output hello.mp3