GPT-4o mini TTS — room for your next idea

curl -X POST 'https://ai.im.inc/api/v1/audio/tts' \
  -H "Authorization: Bearer $IMMERSIVE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "async": true,
  "input": "An idea can start anywhere. With a shape. A colour. A few words. Bring it to life with image, video, audio, text and 3D models, all through Immersive AI. One API. Room for your next idea.",
  "model": "gpt-4o-mini-tts",
  "speed": 1,
  "voice": "coral",
  "provider": "openai"
}'

# Set JOB_ID to the response's "id", then poll every few seconds until the job has finished:
curl "https://ai.im.inc/api/v1/audio/$JOB_ID" \
  -H "Authorization: Bearer $IMMERSIVE_API_KEY"

# The finished response has the result at url.

const headers = { Authorization: `Bearer ${process.env.IMMERSIVE_API_KEY}` };

const response = await fetch("https://ai.im.inc/api/v1/audio/tts", {
  method: "POST",
  headers: { ...headers, "Content-Type": "application/json" },
  body: JSON.stringify({
    "async": true,
    "input": "An idea can start anywhere. With a shape. A colour. A few words. Bring it to life with image, video, audio, text and 3D models, all through Immersive AI. One API. Room for your next idea.",
    "model": "gpt-4o-mini-tts",
    "speed": 1,
    "voice": "coral",
    "provider": "openai"
  }),
});
const job = await response.json();

// Poll every few seconds while the job is still running.
const running = ["pending", "queued", "submitted", "starting", "processing", "running", "streaming", "in_queue", "in_progress"];
let result;
do {
  await new Promise((resolve) => setTimeout(resolve, 5000));
  result = await (await fetch(`https://ai.im.inc/api/v1/audio/${job.id}`, { headers })).json();
} while (running.includes(String(result.status).toLowerCase()));

console.log(result.url);

import os
import time

import requests

headers = {"Authorization": f"Bearer {os.environ['IMMERSIVE_API_KEY']}"}

job = requests.post(
    "https://ai.im.inc/api/v1/audio/tts",
    headers=headers,
    json={
        "async": True,
        "input": "An idea can start anywhere. With a shape. A colour. A few words. Bring it to life with image, video, audio, text and 3D models, all through Immersive AI. One API. Room for your next idea.",
        "model": "gpt-4o-mini-tts",
        "speed": 1,
        "voice": "coral",
        "provider": "openai",
    },
    timeout=300,
).json()

# Poll every few seconds while the job is still running.
running = {"pending", "queued", "submitted", "starting", "processing", "running", "streaming", "in_queue", "in_progress"}
while True:
    time.sleep(5)
    result = requests.get(f"https://ai.im.inc/api/v1/audio/{job['id']}", headers=headers, timeout=60).json()
    if str(result.get("status", "")).lower() not in running:
        break

print(result["url"])

{
    "id": "3dd976d0-acfe-4278-8818-a6782a5f65ba",
    "url": "https://s3.eu-central-1.amazonaws.com/ai.im.inc/examples/outputs/6a98f239-6fc9-479b-be09-4a55bec03697/result.mp3",
    "status": "succeeded",
    "speech_id": "3dd976d0-acfe-4278-8818-a6782a5f65ba"
}

Your browser blocked the clipboard. Select the text and copy it by hand.