We use cookies to enhance your experience, provide personalised content, and analyse our traffic; see our Cookie Policy.
minimax/minimax-music-coverYour song, another style — melody kept, 219 F
Give it a track and a description of where you want it to go: another genre, another voice, another arrangement. The melody survives; everything around it changes. You can replace the words at the same time.
The tune stays recognisable; the production does not
Change genre, voice, instruments and arrangement at once
Supply new words to replace the originals
Generation is a job: you poll for the finished track
Gentle acoustic version: female vocal, nylon guitar, light percussion, slowed tempo.
A danceable afrobeats take on my demo: tight drums, round bass, backing vocals.
Same melody as roots reggae, deep male vocal, organ and restrained brass.
Gospel a cappella: choir alone, handclaps, no instruments at all.
Yes. Top up your Tchavi account with Orange Money, MTN MoMo, M-Pesa or another mobile money operator. No bank card is needed. Credits land as soon as the payment is confirmed and are deducted as you use them.
Yes. Keep your current OpenAI SDK, just change the base URL to Tchavi's (shown in the API tab) and use your Tchavi key. The rest of your code stays the same.
import Tchavi from '@tchavi/sdk';
const client = new Tchavi({ apiKey: 'API_KEY' });
const job = await client.music.generations.create({
"model": "minimax-music-cover",
"prompt": "Same melody, afrobeats arrangement, warm bass and talking drum",
"source_audio_url": "https://your-host.example.com/original-song.mp3"
});
console.log('Job id:', job.id);
console.log('Credits used:', job.tchavi.credits_used);
// Poll for completion
let result = await client.jobs.retrieve(job.id);
while (result.status === 'pending' || result.status === 'processing') {
await new Promise((r) => setTimeout(r, 2000));
result = await client.jobs.retrieve(job.id);
}
console.log('Track URL:', result.output?.audio_url);Every parameter this model accepts on the API. Check the SDK for full typings.
modelRequiredTTS model (e.g. `minimax-music-cover`).
inputRequiredThe text to synthesize.
voiceRequiredVoice timbre: `alloy`, `ash`, `ballad`, `cedar`, `coral`, `echo`, `fable`, `marin`, `nova`, `onyx`, `sage`, or `shimmer`.
response_format"mp3"Audio container format.