Text to Music AI Models
Generate full songs with vocals or instrumental tracks from a prompt and lyrics, with MiniMax Music, Google Lyria, ElevenLabs Music and Stable Audio.
All Text to Music AI Models
Preview the output style, compare capabilities, then open any model for full specs, pricing, and a live Playground.
Lyria 3.5
Lyria 3.5 is Google's flagship music generation model for full-length songs up to a few minutes, with verses, choruses, bridges, expressive vocals, timed lyrics, and rich instrumental arrangements. It...
MiniMax Music 2.6
MiniMax Music 2.6 by MiniMax composes a full song with vocals and accompaniment from a style prompt and lyrics, or an instrumental track without lyrics.
MiniMax Music 3
MiniMax Music 3 by MiniMax composes a complete song up to five minutes long with expressive vocals and evolving arrangements from a style prompt and lyrics.
ElevenLabs Music
Music is ElevenLabs's AI audio generation model. Produce high-quality music tracks, sound effects, and audio landscapes from natural language prompts.
ElevenLabs Music v2
ElevenLabs Music v2 generates studio-quality songs and instrumentals with vocals from a text prompt, up to 10 minutes long.
ElevenLabs Music v2.5
ElevenLabs Music v2.5 generates studio-quality songs and instrumentals with vocals from a text prompt, up to 10 minutes long.
Stable Audio 3 Small Music
Stable Audio 3 Small Music by Stability AI is a fast, low-cost music generator producing tracks up to 2 minutes from a text prompt.
Songs and soundtracks from a prompt
Music models compose a track from a style prompt, and many also accept lyrics for sung vocals.
- MiniMax Music 3: complete songs up to five minutes with expressive vocals and evolving arrangements.
- MiniMax Music 2.6: full songs from a style prompt and lyrics, or instrumentals.
- Lyria 3.5 (Google): full-length songs with verses, choruses and bridges.
- ElevenLabs Music v2 and v2.5: songs and instrumentals with vocals, up to 10 minutes.
- Stable Audio 3 Small Music: fast, low-cost tracks up to 2 minutes.
Need speech instead? See text-to-speech models.
Start using Text to Music AI Models on SandBase
One API key and one request shape for every model on this page.
- 01
Create an API key
Sign in to the SandBase Console and create a key on the API Keys page. Keep it in an environment variable and never commit it to source control.
TERMINALexport SANDBASE_API_KEY="YOUR_SANDBASE_API_KEY" - 02
Submit a run
Send a request to the Unified Run API with model minimax/music/2.6. Only the model field changes between models on this page.
TERMINALcurl https://api.sandbase.ai/v1/run \ -H "Authorization: Bearer $SANDBASE_API_KEY" \ -H "Content-Type: application/json" \ -d '{"model": "minimax/music/2.6", "prompt": "Upbeat indie pop, bright guitars, female vocal"}' - 03
Fetch the result
The response includes a run id. Poll it every few seconds until the status is completed, then download the output URL.
TERMINALcurl https://api.sandbase.ai/v1/run/$RUN_ID \ -H "Authorization: Bearer $SANDBASE_API_KEY"
Questions, answered
Can I provide my own lyrics?
Yes, on models that accept lyrics, such as MiniMax Music. Other models write vocals from the prompt.
How long can a track be?
Up to 2 minutes on Stable Audio 3 Small, about five minutes on MiniMax Music 3, and up to 10 minutes on ElevenLabs Music v2/v2.5.
Can I generate instrumentals only?
Yes. Most models support instrumental output; describe it in the prompt or use the instrumental option.
What format is returned?
An audio file URL, usually MP3.
Build with Text to Music AI Models.
One key, consistent APIs, and usage-based pricing across every model on this page.