AI MODEL DISCOVERY
TypeSafeTypeSafe Jev 1.13
Structured decisions from text or JSON, with yes/no probabilities, choices and scores.
Describe a mood, a scene or a musical idea, then create music with SeeAPI. Explore AI Music M1, M2 and M3 to generate vocal songs or instrumental soundtracks from a text brief.
PROVIDERS
Start with a description and musical style, then listen to what the models create.
Write the atmosphere, instruments and genre you want. Send a style and prompt in normal mode to start the generation.
Alibaba
Black Forest Labs
ByteDance
Google
Grok
Kling
Lightricks
MiniMax
OpenAI
PixVerse
Runway
Vidu{
"model": "ai-music-m2",
"endpoint": "music-generation",
"input": {
"custom_mode": false,
"instrumental": true,
"style": "Warm lo-fi piano",
"prompt": "A quiet evening by the window."
}
}Use instrumental output for background music, or request a song with vocals from your description.
Read task status and stage updates. Preview available audio while processing, then retrieve the completed tracks.
GET /v1/generations/{id}
processing → text
processing → first
succeeded → completeEach generation includes all tracks returned for that task, with audio, lyrics and cover artwork when available.
A text to music workflow for your application.
Compare AI Music M1, M2 and M3 using the same musical brief. Check each model's input limits and current API price, then listen for the atmosphere, instrumentation and vocal delivery your project needs.
Put genre, mood and instruments in style, and the scene or song idea in prompt. For example, try gentle piano for an evening reading scene. Use custom_mode: false; instrumental selects music with or without vocals.
Poll the task or receive callbacks. Preview music when a playback URL is available, then use succeeded status to collect all result.assets. Keep each track's ID alongside its audio, lyrics and cover when provided.
Turn user descriptions into listening options inside your product.
Let users describe a quiet evening, a celebration or a new adventure, then compare the generated tracks.
Describe the scene and musical atmosphere to create instrumental options for an editing project.
Generate music concepts for a menu, location or story moment using genre and instrument descriptions.
Describe a restrained instrumental arrangement for spoken content. Listen beneath your narration and compare whether the melody, energy and instrumentation leave enough room for the voice.
Turn a product's mood into a musical brief: bright and playful, calm and reassuring, or bold and energetic. Compare candidate tracks before choosing a direction for your project.
Let users move from a short idea to a listening shortlist. Save the brief with each task and change one musical detail at a time to explore alternatives.
Practical details for choosing a model and integrating music generation.
Describe the mood, genre and instruments in style, and use prompt for the scene or song idea. A clear musical brief helps you compare results across models.
Open the API reference for model parameters and response examples, or compare the current credit price for each model.