Overview
Suno turns a written description into a finished song — vocals, instrumentation and structure together — and then lets you keep working on it. The generation side runs on the web, iOS and Android; the editing side is Suno Studio, a browser-based production suite. Suno describes itself as "a music company building the world's first creative entertainment platform", says over two thirds of its team are musicians, and reports that more than 100 million people have made music on the service since the company was founded in 2022.
The current model generation is Suno v6, announced 9 September 2026, and it is the first Suno built with record labels as licensing partners: the training data is licensed from Warner Music Group, BMG and Believe, and Suno states that v6 is not trained on the data behind its earlier models. Three variants ship together — a base v6 aimed at polished, controllable output, a v6-wild tuned for unpredictable and textured results, and a faster v6-mini. Suno says it will retire the previous generation as v6 rolls out.
Editing is where Suno differs from a pure prompt-to-audio service. v6 accepts a plain-language instruction to rewrite part of a track or change a single lyric without regenerating the whole song, and it can take text, audio, images or video as reference material. Suno Studio 2.0, released to Premier subscribers on 13 August 2026, adds MIDI on a timeline with a wavetable synth, high-fidelity stem separation, factory audio effects such as sidechain compression and convolution reverb, automation curves, and a beta chat bar that acts as a production collaborator. Uploaded audio and lyrics are screened for unauthorized use.
What it does
- Text-to-song generation with vocals, instrumentation and arrangement in one pass
- Three v6 models: v6 for controlled results, v6-wild for unpredictable ideation, v6-mini for speed
- Trained on catalogues licensed from Warner Music Group, BMG and Believe
- Edit part of a finished track, or change one lyric, with a plain-language instruction
- Reference inputs in text, audio, image or video form, plus mashups across tracks
- Suno Studio 2.0 (Premier): MIDI timeline, wavetable synth, stem separation, effects, automation curves and a beta chat bar
- Commercial-use rights and song downloads on the paid plans; screening of uploaded audio and lyrics
Getting started
Suno is a hosted product, not a package you install. Every plan runs in the browser or the mobile apps; the model you get depends on your tier.
Open Suno and start on the free tier
The free plan gives 50 credits per day and runs v6-mini. Free-tier songs cannot be downloaded and carry no commercial rights.
https://suno.comUpgrade for the full v6 models
Pro is $8 per month with 2,500 credits and 20 song downloads; Premier is $24 per month with 10,000 credits and 60 downloads. Both include commercial use and unlock v6 and v6-wild.
https://suno.com/pricingEdit instead of regenerating
Describe the change you want — a different bridge, one reworded line — rather than starting the prompt over. You can also feed the model an image, a video or an audio clip as a reference.
Rewrite the second verse as a slower, sparser piano partOpen Suno Studio for production work
Premier subscribers get Studio 2.0 in the browser: MIDI on the timeline, stem separation, plugins and automation, plus unlimited multitrack and stem export.
https://suno.com/blog/studio-2Commands and code are distilled from the project's own documentation — always check the official docs for the latest.
When to use it
- Sketching a full song from a written idea before committing studio time to it
- Producing background and theme music for video, games or podcasts with commercial rights on a paid plan
- Pulling a single instrument out of a reference track and building a new beat around it
- Taking a generated draft into a browser DAW for MIDI, effects and automation work rather than exporting to another tool
Suno in the news
- 2026-09-09MAJORSuno v6 — a music model family trained only on licensed catalogues
- 2026-08-13MAJORSuno Studio 2.0 — browser music workstation adds MIDI and a chat bar
- 2026-07-31MAJORSuno loses copyright case to GEMA — Munich court rules AI music training infringed
- 2026-07-15MAJORSuno hacked — leak exposes customer data and reveals YouTube and Deezer music scraping
From the AI/TLDR release feed — every item is source-verified when it ships.
How Suno compares
Suno alongside other open-source audio, music & voice tools AI/TLDR tracks, ranked by GitHub stars.
| Tool | Stars | What it does |
|---|---|---|
| Whisper | ★ 109k | OpenAI's speech recognition model that transcribes and translates audio across many languages. |
| GPT-SoVITS | ★ 61.7k | An open-source WebUI that clones a voice from a short audio sample and turns text into speech, with zero-shot and few-shot fine-tuning. |
| VibeVoice | ★ 54.1k | Microsoft's text-to-speech model for generating long, expressive multi-speaker audio like podcasts. |
| Coqui TTS | ★ 46k | A library of text-to-speech models including the multilingual XTTS voice-cloning model. |
| ChatTTS | ★ 39.8k | ChatTTS is an open-source text-to-speech model tuned for dialogue, with multi-speaker support and fine-grained control over laughter, pauses, and prosody. |
| OpenVoice | ★ 37.5k | OpenVoice clones a voice from a short reference clip and speaks in multiple languages, with control over emotion, accent, rhythm, and intonation. |
| MockingBird | ★ 36.9k | An open-source PyTorch toolbox that clones a voice from a short sample and generates Mandarin Chinese speech, with a web app, desktop toolbox, and command line. |
| Suno | — | AI music platform that writes complete songs with vocals from a prompt, plus a browser DAW for editing the result |