MiniMax Music

MiniMax Music is a text-to-music generation model: give it a prompt describing the song you want ('upbeat lofi hip-hop with mellow piano, 90 BPM, calm focus mood'), optionally with lyrics, and it composes and renders a complete track. New category for the catalog. Use for background music in video content, marketing audio, podcast intros, and any place you'd otherwise license a stock-music track. Output format is mp3; typical render time 30-90 seconds.

Quick start

Use any OpenAI-compatible client. Just change base_url and your key.

from openai import OpenAI

client = OpenAI(
    api_key="tl-xxxxxxxxxxxxxxxxxxxxxxxx",
    base_url="https://api.thalam.ai/v1",
)

response = client.chat.completions.create(
    model="minimax/music",
    messages=[
        {"role": "user", "content": "Hello from Thalam!"}
    ],
)

print(response.choices[0].message.content)