import time
import requests

resp = requests.post(
    "https://modelxing.com/v1/audio/speech",
    headers={"Authorization": "Bearer YOUR_API_KEY"},
    json={"model": "qwen3-tts-instruct-flash", "voice": "Cherry", "input": "Hello from XModel", "response_format": "wav"},
)

if resp.status_code == 200:
    # Short text — audio returned directly
    with open("output.wav", "wb") as f:
        f.write(resp.content)
else:
    # Long text — job submitted (202), poll until done
    job_id = resp.json()["id"]
    while True:
        poll = requests.get(
            f"https://modelxing.com/v1/audio/speech/jobs/{job_id}",
            headers={"Authorization": "Bearer YOUR_API_KEY"},
        ).json()
        if poll["status"] == "succeeded":
            print("Audio ready:", poll["audio"]["url"])
            break
        elif poll["status"] == "failed":
            print("Job failed:", poll["error"])
            break
        time.sleep(3)