Vocals and lyrics
Make full songs with singing, or provide your own lyrics.
ElevenLabs Music is an AI music generator that makes full songs, with vocals, lyrics and instrumentals, from a short description. On avots.ai you can use it online from one balance, so sign up and make a track in a minute.
ElevenLabs Music is a top pick for AI songs. Here is what you get on avots.ai.
Make full songs with singing, or provide your own lyrics.
Describe a style and get a matching track.
Skip the vocals for background music and jingles.
Generate short clips or longer tracks.
Run it in the cloud with no setup.
Use it next to Stable Audio, MusicGen and Lyria without extra accounts.
No separate account, no extra API key, no subscription. Create one avots account and the same balance works everywhere.
Open app.avots.ai, pick the model, write a prompt, download the result. Works on desktop and mobile.
Create from your phone in @AvotsAIbot. Same models, same balance.
Call it from Claude, Cursor or Cline through the avots MCP server.
Script it into your own app with the OpenAI compatible API and one key.
| ElevenLabs Music | Stable Audio 2.5 | MusicGen | Lyria | |
|---|---|---|---|---|
| Vocals | yes | limited | no | limited |
| Lyrics | yes | no | no | no |
| Instrumentals | yes | yes | yes | yes |
| On avots.ai | live now | live now | live now | live now |
All of these audio models run on avots.ai from one balance, so you can compare ElevenLabs Music against Stable Audio and MusicGen on the same idea.
1,000 tokens cost 0.99 EUR and cover several tracks. No subscription. ElevenLabs Music sits on the same balance as Stable Audio, MusicGen and the video and image models.
Sign up and create ✦Google Gemini image model for photoreal images and edits. Live now.
Google Veo, realistic AI video with sound. Live now.
ByteDance video with native audio and reference to video. Live now.
OpenAI Sora, strong physics and longer shots. Live now.
FLUX 1.1 Pro and FLUX.2 for photoreal images. Live now.
Kuaishou's Kling video model, strong motion. Live now.
And many other models. avots.ai runs 40+ AI models for chat, image, video and audio on one balance. See the full list on the Tools page, or open the app and start creating.
From 31 real runs by 1 people on avots.ai over the last 120 days.
100% — 31 of 31 runs returned a result.
Usually about 15 seconds. The spread we saw: 10 to 22 seconds.
90 tokens for a 5-second clip
A run that fails is refunded automatically, so a failure costs you nothing. Updated 30.09.2026.