Audio Generation

Available audio models

Text-to-speech

Model slug	Display name	Tasks
`eleven-v3`	ElevenLabs v3	text-to-speech
`qwen3-tts`	Qwen3 TTS	text-to-speech

Text-to-music

Model slug	Display name	Tasks
`music-2.5`	MiniMax Music 2.5	text-to-music

For the full list, see the model catalog.

Text to speech

Generate natural-sounding speech from text.

cURL

curl -X POST https://aircube.ai/api/v3/eleven-v3/text-to-speech \
  -H "Authorization: Bearer $AIRCUBE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "Hello! Welcome to AirCube, the unified API for AI generation."
  }'

Python

import os
import time
import requests

API_KEY = os.environ["AIRCUBE_API_KEY"]
BASE_URL = "https://aircube.ai/api/v3"
HEADERS = {
    "Authorization": f"Bearer {API_KEY}",
    "Content-Type": "application/json",
}

# Submit
response = requests.post(
    f"{BASE_URL}/eleven-v3/text-to-speech",
    headers=HEADERS,
    json={
        "prompt": "Hello! Welcome to AirCube, the unified API for AI generation.",
    },
)
generation_id = response.json()["data"]["id"]

# Poll
while True:
    result = requests.get(f"{BASE_URL}/status/{generation_id}", headers=HEADERS).json()
    if result["data"]["status"] == "completed":
        print(result["data"]["output_url"])
        break
    elif result["data"]["status"] == "failed":
        print("Failed")
        break
    time.sleep(3)

JavaScript

const API_KEY = process.env.AIRCUBE_API_KEY;
const BASE_URL = "https://aircube.ai/api/v3";

const submitRes = await fetch(`${BASE_URL}/eleven-v3/text-to-speech`, {
  method: "POST",
  headers: {
    Authorization: `Bearer ${API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    prompt: "Hello! Welcome to AirCube, the unified API for AI generation.",
  }),
});
const { data } = await submitRes.json();

while (true) {
  const pollRes = await fetch(`${BASE_URL}/status/${data.id}`, {
    headers: { Authorization: `Bearer ${API_KEY}` },
  });
  const result = await pollRes.json();
  if (result.data.status === "completed") {
    console.log(result.data.output_url);
    break;
  } else if (result.data.status === "failed") {
    throw new Error("Failed");
  }
  await new Promise((r) => setTimeout(r, 3000));
}

Text to music

Generate music from a text description.

cURL

curl -X POST https://aircube.ai/api/v3/music-2.5/text-to-music \
  -H "Authorization: Bearer $AIRCUBE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "upbeat electronic lo-fi beat with soft piano chords, 120 BPM"
  }'

Python

response = requests.post(
    f"{BASE_URL}/music-2.5/text-to-music",
    headers=HEADERS,
    json={
        "prompt": "upbeat electronic lo-fi beat with soft piano chords, 120 BPM",
    },
)
generation_id = response.json()["data"]["id"]

while True:
    result = requests.get(f"{BASE_URL}/status/{generation_id}", headers=HEADERS).json()
    if result["data"]["status"] == "completed":
        print(result["data"]["output_url"])
        break
    elif result["data"]["status"] == "failed":
        print("Failed")
        break
    time.sleep(3)

JavaScript

const submitRes = await fetch(`${BASE_URL}/music-2.5/text-to-music`, {
  method: "POST",
  headers: {
    Authorization: `Bearer ${API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    prompt: "upbeat electronic lo-fi beat with soft piano chords, 120 BPM",
  }),
});

Parameters

voice

For text-to-speech models, you can specify a voice ID:

{
  "prompt": "Welcome to our podcast.",
  "voice": "voice-id-here"
}

Available voice IDs depend on the model. Check the model's documentation for supported voices.

prompt tips

For TTS:

Use natural punctuation to control pacing and intonation.
Longer texts produce longer audio — cost scales accordingly.

For music:

Describe the genre, tempo, instruments, and mood.
Include BPM for more precise tempo control.
Example: "cinematic orchestral score with strings and brass, slow build, 80 BPM"

Audio Generation

On this page