ElevenLabs Music - Kyma API

Overview

This model converts text prompts into audio, supporting both lyrical and instrumental requests. It accepts a 2000-token context window and produces audio outputs up to five minutes per generation. On Kyma, the model runs on the premium tier with slower generation speeds. It supports prompt caching, which bills repeated prefixes at this model’s cached input rate. Responses return exact generation cost in usage.cost and identify the active model via the X-Kyma-Model header, with automatic failover handling routing if a path degrades. The model does not support reasoning, vision, or structured outputs. It accepts text-only input and returns audio-only output. It is optimized for batch or asynchronous generation rather than real-time streaming.

Specs

Field	Value
Model ID	`elevenlabs-music`
Best for	Background music, soundtracks, theme generation, royalty-free music
Context window	2,000
Input modalities	Text
Output modalities	Audio
Tool calling	Yes
Structured outputs	Yes
Prompt caching	Yes
Speed	Slow
Cost band	Premium
Release stage	Stable

Pricing

	Per 1M tokens
Input	$0.20
Output	$0.60

Use this when

Generate background tracks — Create royalty-free audio for videos, games, or applications.
Build custom soundtracks — Produce instrumental or lyrical compositions up to five minutes.
Prototype theme music — Iterate on text prompts to test audio concepts before final production.
Automate content audio — Integrate prompt-driven music generation into media pipelines.

Not ideal for

Do not use this model for real-time audio streaming, speech synthesis, or latency-sensitive interactive voice applications.

Pick something else when

You need fast speech synthesis: use eleven-flash-v2-5 or eleven-turbo-v2-5.
You need high-fidelity voice cloning: use minimax-voice-clone or eleven-v3.
You need sound effects instead of music: use elevenlabs-sfx.
You need lower-cost music generation: use minimax-music or minimax-music-pro.

Example

from openai import OpenAI

client = OpenAI(base_url="https://kymaapi.com/v1", api_key="ky-...")

response = client.chat.completions.create(
    model="elevenlabs-music",
    messages=[{"role": "user", "content": "..."}],
)

Agent query example

Ask the API which models fit, instead of hardcoding an id:

curl "https://kymaapi.com/v1/models?recommended_for=generate-speech&tools=true&quality_tier=frontier-open"

FAQ

Can I pass lyrics to the prompt? Yes, the model accepts text prompts describing lyrics or instrumental arrangements to generate audio. How does prompt caching work for this model? Kyma bills repeated prompt prefixes at this model’s cached input rate. What happens if the generation endpoint fails? Kyma automatically reroutes the request to a healthy serving path without requiring client-side retries.

​Overview

​Specs

​Pricing

​Use this when

​Not ideal for

​Pick something else when

​Example

​Agent query example

​FAQ