Skip to main content

Turn free-form musical ideas into structured prompts for text-to-music workflows.

Project description

Text-to-Music Prompt Structurer

PyPI version License: MPL 2.0

Turn free-form musical ideas into structured prompts for text-to-music workflows.

The package detects genre, mood, BPM, key, instruments, production details, language, voice type, vocal tone, and vocal technique. It has no runtime dependencies and requires Python 3.10 or later.

Install

python -m pip install text-to-music-prompt-structurer

Command line

text-to-music-prompt "neo soul with piano, warm breathy female alto vocals in Spanish, intimate and melismatic, in d minor, nostalgic, 92 bpm"

Output:

STYLE: Soul / Neo Soul
MOOD: Nostalgic, Warm
BPM: ~92
KEY: D Minor
INSTRUMENTS: Piano
PRODUCTION: Warm tone
VOCALS:
  LANGUAGE: Spanish
  VOICE TYPE: Female Lead, Alto
  TONE: Warm, Breathy, Intimate
  STYLE: Melismatic vocals

Python

from text_to_music_prompt_structurer import MusicPromptEngine, format_prompt

prompt = MusicPromptEngine().process(
    "synthwave with 808, dark and dreamy, female vocals in English"
)

print(format_prompt(prompt))

Output:

STYLE: Synthwave
MOOD: Dark, Dreamy
INSTRUMENTS: 808 Bass
PRODUCTION: Dark tone
VOCALS:
  LANGUAGE: English
  VOICE TYPE: Female Lead
  TONE: Dark

process() returns a MusicPrompt object, so applications can use each detected value directly instead of parsing the formatted text. Its fields cover:

  • Musical direction: genre, subgenre, mood, energy, tempo, bpm, and key.
  • Arrangement and sound: instruments, production, rhythm, structure, and era.
  • Vocal direction: language, voice_type, vocal_tone, and vocal_style.

format_prompt() renders only the detected fields as a ready-to-use structured prompt.

Development

git clone https://github.com/edujbarrios/text-to-music-prompt-structurer.git
cd text-to-music-prompt-structurer
python -m pip install -e ".[dev]"
python -m pytest
ruff check .

See CONTRIBUTING.md to add vocabularies or detection strategies. Release history is available in CHANGELOG.md.

License

Copyright © 2026 Eduardo J. Barrios.

This project is licensed under the Mozilla Public License 2.0. MPL 2.0 is a file-level copyleft license: modifications to covered source files must remain available under MPL 2.0, while those files may be combined with code under other licenses. See NOTICE for attribution details.

[!NOTE] This is an unofficial tool and is not affiliated with, endorsed by, or connected to Suno AI.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

text_to_music_prompt_structurer-0.1.1.tar.gz (31.4 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

text_to_music_prompt_structurer-0.1.1-py3-none-any.whl (34.3 kB view details)

Uploaded Python 3

File details

Details for the file text_to_music_prompt_structurer-0.1.1.tar.gz.

File metadata

File hashes

Hashes for text_to_music_prompt_structurer-0.1.1.tar.gz
Algorithm Hash digest
SHA256 58a6508de317ea0fba42fc45336399a06ff41a8764f1e52b87c317aa7bb2390e
MD5 1032c5d1b4d3671a79b4d8b4ddc50d8c
BLAKE2b-256 e6c082c0ba3ba5904fcb1472677dbe80fbb16df19df1ad1ba143699969de771d

See more details on using hashes here.

File details

Details for the file text_to_music_prompt_structurer-0.1.1-py3-none-any.whl.

File metadata

File hashes

Hashes for text_to_music_prompt_structurer-0.1.1-py3-none-any.whl
Algorithm Hash digest
SHA256 9a734d1b2e462c04c1e9a250afdfa378ab79c9f7e8d7e582a83a3acd20b2f0f4
MD5 6e38c5d4efedafb8126055bf02bc2b83
BLAKE2b-256 c815202e5183c0a2987b693fc2d84de63f329f84588278673f794e5510a073c4

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page