cURL TTS API quickstart: first Audra MP3 in 60 seconds — Audra

Wire Audra like any authenticated HTTP TTS dependency — secrets, retries, and clear limits. Not for realtime voice agents or cloning.

Who this is for

Integration notes: curl quickstart

Treat Audra like any authenticated HTTP TTS dependency — secrets in env, retries with backoff, and idempotency keys on production POSTs. Sync accepts up to 50k characters; longer scripts use POST /v2/speech/jobs.

JavaScript
import OpenAI from "openai";
import { writeFile } from "node:fs/promises";

const client = new OpenAI({
  apiKey: process.env.AUDRA_API_KEY,
  baseURL: "https://audratalks.com/v1",
});

const speech = await client.audio.speech.create({
  model: "audra-essential",
  voice: "june",
  input: "Hello from Audra.",
});

await writeFile("out.mp3", Buffer.from(await speech.arrayBuffer()));
Python
from openai import OpenAI
import os

client = OpenAI(
    api_key=os.environ["AUDRA_API_KEY"],
    base_url="https://audratalks.com/v1",
)

with client.audio.speech.with_streaming_response.create(
    model="audra-essential",
    voice="june",
    input="Hello from Audra.",
) as response:
    response.stream_to_file("out.mp3")
curl
curl https://audratalks.com/v2/speech \
  -H "Authorization: Bearer sk-live-YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"audra-essential","text":"Hello from Audra.","voice":"june","format":"mp3"}' \
  --output out.mp3

Cost sanity check

Want to hear a sample on your own script? Get an API key at /dashboard — 25k free characters, no card.

FAQ

Is Audra OpenAI-compatible?

Yes. Point the OpenAI SDK at https://audratalks.com/v1 with model audra-essential — copy-paste on /migrate.

What does QA-gated billing mean?

Credits finalize only after automated QA passes. Failed renders refund automatically.

Does Audra support realtime voice agents?

No. Audra is a batch TTS API for mastered MP3/WAV files. For sub-200ms conversational agents, stay on a realtime-oriented provider.

Can I clone a custom brand voice?

No. Audra ships preset voices only. Use ElevenLabs (or similar) when cloning is a hard requirement — see /vs/elevenlabs.

Next steps