musicNEW

ElevenLabs Music

ElevenLabs Music composes a finished track from a written brief: genre, mood, instrumentation and the feel you are after. The difference from most music models is that you set the length, anywhere from 3 seconds to 10 minutes, and the track comes back at exactly that length. Billing follows it, charged by the second, so a 5 second sting and a 3 minute bed are priced honestly against each other instead of costing the same. It renders in a few seconds and returns 48 kHz audio, which is high enough to sit under finished video without resampling. Use it for scores, beds, stings and loops where you already know the duration the edit needs.

Pricing

Input

$0.150 / min

Output

Pay only for what you use. No subscriptions, no minimums.

Specs

Context
Max output
10 min
Latency
Fast
Category
Arabic
Partial

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="elevenlabs/music",
    messages=[
        {"role": "user", "content": "Hello from Thalam!"}
    ],
)

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

Similar models

MiniMax Music

NEWMusic

Text-to-music generation. Describe the song you want: genre, mood, instrumentation, lyrics, and the model composes and renders a track.

Context
Max output
Latency
Medium
Input price
$0.150 / song
Output price

More from ElevenLabs

All ElevenLabs models (3)