Text to Music
Turn a detailed music description and structured lyrics into an original WAV song with MiniMax Music 3.
Save your music
Log in to create and manage your AI music.
Community music
[instrümental:Kemençe,davul,darbuka][Pre-Chorus][sad,longing][Verse - Deep Vocal with Echo][Chorus - Layered Harmonies] Verse1] ooooof ,oofff,of,of(echoing, fading) ooooof ,oofff,of,of(echoing, fading) [Verse 1] Yalnız içme rakıdan zevk alamazsın(alamazsın) bensiz hayata Neşe katamazsın(kaaatamazsın) Bülentim mum gibi eridi köşelerde(ooooof ,oofff) Aşkın ateşini su ile söndüremezsin(çakmağı
[instrümental:Kemençe,davul,darbuka][Pre-Chorus][sad,longing][Verse - Deep Vocal with Echo][Chorus - Layered Harmonies] Verse1] ooooof ,oofff,of,of(echoing, fading) ooooof ,oofff,of,of(echoing, fading) [Verse 1] Yalnız içme rakıdan zevk alamazsın(alamazsın) bensiz hayata Neşe katamazsın(kaaatamazsın) Bülentim mum gibi eridi köşelerde(ooooof ,oofff) Aşkın ateşini su ile söndüremezsin(çakmağı
bülent,rakı,saki,acı,efe,zeybek [instrümental:Kemençe,davul,darbuka][Pre-Chorus][sad,longing][Verse - Deep Vocal with Echo][Chorus - Layered Harmonies]
bülent,rakı,saki,acı,efe,zeybek [instrümental:Kemençe,davul,darbuka][Pre-Chorus][sad,longing][Verse - Deep Vocal with Echo][Chorus - Layered Harmonies]
Artık yaşadığım hazan mevsimi Dökülmüşüm beni böyle kabul et Etten kemiktenim çınar değilim Bükülmüşüm beni böyle kabul et İçimde zemheri, yok yazım artık Duyulmaz feryadım, avazım artık Toparlanmam muhal, enkazım artık Yıkılmışım beni böyle kabul et Sürura, huzura, keyfe, neşeye Uzağım dünyaya dair her şeye Durgun gönlümdeki izbe köşeye Çekilmişim beni böyle kabul et
Artık yaşadığım hazan mevsimi Dökülmüşüm beni böyle kabul et Etten kemiktenim çınar değilim Bükülmüşüm beni böyle kabul et İçimde zemheri, yok yazım artık Duyulmaz feryadım, avazım artık Toparlanmam muhal, enkazım artık Yıkılmışım beni böyle kabul et Sürura, huzura, keyfe, neşeye Uzağım dünyaya dair her şeye Durgun gönlümdeki izbe köşeye Çekilmişim beni böyle kabul et
How does text to music work?
Text to music converts two written inputs into a song: a creative brief for the sound and lyrics for the vocal content. In Story321, the text to music form asks for genre, mood, vocal style, instruments, tempo, key, and arrangement in the prompt, then uses separately structured lyrics to guide the song sections. Select an upper duration limit, generate, review the completed WAV, and download it from your Music history. Text to music is most useful when you describe decisions precisely, such as how an intro begins, what changes in the chorus, or which instruments should carry the final section.
Text to music inputs with clear creative roles
Music description
The prompt defines the sound. Include style, mood, tempo, key, vocal color, instruments, arrangement, and an emotional progression rather than relying on a single genre word.
Lyrics field
The lyrics field defines what is sung. Use your own words and place [intro], [verse], [chorus], [bridge], [instrumental], or [outro] tags on their own lines.
Duration selection
The tool supports 30, 60, 120, 180, and 300 second requests. Each option shows its credit charge before you generate.
Focused controls
The first release keeps sampling controls out of the form. This lets the text to music workflow focus on the direction, lyrics, duration, and visibility that shape the request.
WAV output
The tool saves the completed 44.1 kHz, 16-bit stereo WAV in the Music workspace, where it can be played and downloaded.
Workspace history
Each result keeps the prompt, lyrics metadata, selected model, duration, visibility, and downloadable output together for later review.
Why use text to music for a first draft?
Move from words to an audible concept
The workflow helps a lyric, mood board, or production note become something listeners can react to. That makes feedback more specific than a written description alone.
Test arrangement choices
Create variations by changing one part of the brief: move from piano to guitar, slow the tempo, change vocal tone, or alter the chorus lift.
Keep a repeatable brief
Saved prompts make it easier to revisit a useful direction. Keep what worked, then adjust the lyric structure or arrangement in the next version.
See the cost before generation
The workflow charges 0.5 credits per selected second, with a 15-credit minimum. The available durations map directly to 15 through 150 credits.
How to create text to music
- 1
Describe the track
Write a prompt with the musical traits that matter. Mention the genre, energy, tempo, instruments, vocal delivery, and how sections should develop.
- 2
Format the lyrics
Add original lyrics beneath separate section tags. A clear verse and chorus structure gives the model a practical map for the vocal material.
- 3
Select time and privacy
Choose a 30 second to five minute upper limit and decide whether the completed result should be private or public.
- 4
Generate and evaluate
Play the WAV in your workspace, inspect the actual duration, and download it if the result works. For a new version, revise the brief with one intentional change.
Text to music examples
Lyric demos
Use the generator to hear how a verse and chorus contrast before arranging a final performance.
Short-form video ideas
Generate a custom text to music sketch for a vertical video concept, title sequence, or social campaign draft.
Story and game concepts
Try text to music for a character theme, scene transition, or narrative cue when a written mood description needs sound.
Pitch presentations
Give a creative pitch an original text to music example that demonstrates energy, pacing, and the intended emotional tone.
Learning exercises
Compare prompt details in text to music: write the same lyric in two styles and listen for how arrangement language affects the output.
Private experimentation
Use private text to music generation for early lyric and arrangement sketches that you do not want shown in the community showcase.
Text to music guidelines
- Use lyrics and directions you are entitled to submit.
- Treat the selected duration as an upper limit; the actual result may end sooner.
- Do not request an exact imitation of a living artist or copyrighted song.
- Review each WAV before publishing, distributing, or using it in an edit.
Related Music pages
AI Music Generator
Explore the Story321 Music workspace.
Open MusicMiniMax Music 3
Read the model-specific text to music page.
Open MiniMax Music 3
Frequently Asked Questions
What is the difference between the text to music prompt and lyrics?
The text to music prompt describes how the song should sound: genre, instruments, tempo, vocal character, key, arrangement, and mood. Lyrics supply the words to sing. Keeping these roles separate makes the request easier to understand and easier for you to revise.
How should I format text to music lyrics?
Put a structure tag on a line by itself, then put the lyric lines below it. For example, use [verse] on one line, the verse below it, then [chorus] on its own line. This preserves the section structure expected by the text to music model.
How long can a text to music track be?
You can choose 30, 60, 120, 180, or 300 seconds. The selected duration is the maximum requested length; the model can return a shorter result when the musical arrangement reaches an endpoint.
How are text to music credits calculated?
Text to music costs 0.5 credits per selected second, with a minimum of 15 credits. The form displays 15, 30, 60, 90, and 150 credits for the five available durations.
What does text to music download?
The completed text to music file is stored and downloaded as 44.1 kHz, 16-bit stereo WAV. You can preview it in the Music workspace before downloading.
Can I keep a text to music result private?
Yes. Turn on private mode before submitting the request. The completed text to music output stays in your workspace history and is not added to the public showcase.
Text to music pricing
- 30 seconds
- 15 credits
- 60 seconds
- 30 credits
- 120 seconds
- 60 credits
- 180 seconds
- 90 credits
- 300 seconds
- 150 credits
Text to music specifications
| Model | MiniMax Music 3 |
|---|---|
| Prompt | Required, up to 2,000 characters |
| Lyrics | Required, up to 3,500 characters |
| Output | 44.1 kHz 16-bit stereo WAV |
Official MiniMax resources
MiniMax Music“Create music from a creative brief and lyrics.”
Music Generation Guide“Review the official music generation workflow.”
Music Generation API“Review API fields for music generation.”
Write your first text to music brief
Describe the sound, add structured lyrics, choose duration, and generate a WAV song.
Create text to music