MiniMax launches Music 1.5 — four-minute full songs, natural vocals, and fine-grained control
MiniMax today unveiled Music 1.5 (branded in some company channels as the Conch music model), a major upgrade to its generative-audio suite that the company says extends generation length and improves vocal realism while adding fine-grained, language-style control for creators. The release positions MiniMax to push AI music beyond short clips toward complete song production workflows.
Key capabilities
- Full-length generation (up to ~4 minutes): Designed to produce a finished-song length that can be used directly in many creative contexts.
- Natural vocals: Simultaneous accompaniment and singing voice generation with clearer timbre and expressiveness than prior releases.
- Fine-grained control: Users can specify or refine style, emotion, scene and even segment-level structure (e.g., write a verse with these lyrics and a chorus with that mood).
- Wide genre & instrument support: From pop, rock and jazz to classical and ethnic instruments — MiniMax says the model includes coverage for niche timbres and non-Western instruments.
- Covering multiple languages and cultures, it can generate music of diverse cultural styles.
- Clear structure: The model outputs music according to a typical song structure, such as Intro – Verse – Chorus – Bridge – Outro, avoiding repetitive sections or monotonous melodies.
- Open API for developers to directly access and use
Behind these breakthroughs lies MiniMax’s accumulated expertise in multimodal processing, including text, voice, and vision. Music 1.5 leverages the power of text models to provide a deeper understanding and control of text descriptions. This not only allows for comprehensive control over song style, emotional tone, and applicable scenarios, but also enables granular control of vocal characteristics, generating vocal tonality with diverse characteristics.
MiniMax Music 1.5 can be widely used in music creation, film and television soundtracks, game sound effects, advertising and marketing, education and training, and corporate scenarios. It not only helps musicians and producers quickly generate complete demos with vocals, but also provides emotionally and context-appropriate soundtracks for film, television, games, and commercials. It also supports educational platforms and creators with stylized practice and content customization, providing efficient and low-cost music solutions for corporate events, brand communications, and interactive experiences.
The release of Music 1.5 not only lowers the barrier to entry for music creation but also returns to the essence of hearing, allowing “good” music to flow naturally.
Getting Started
CometAPI is a unified API platform that aggregates over 500 AI models from leading providers—such as OpenAI’s GPT series, Google’s Gemini, Anthropic’s Claude, Midjourney, Suno, and more—into a single, developer-friendly interface. By offering consistent authentication, request formatting, and response handling, CometAPI dramatically simplifies the integration of AI capabilities into your applications. Whether you’re building chatbots, image generators, music composers, or data‐driven analytics pipelines, CometAPI lets you iterate faster, control costs, and remain vendor-agnostic—all while tapping into the latest breakthroughs across the AI ecosystem.
The latest integration Minimax Music 1.5 will soon appear on CometAPI, so stay tuned！While we finalize Minimax Music 1.5 Model upload, explore our other music models such as Suno Music on the Models page or try them in the AI Playground.
