We use cookies to enhance your experience, provide personalised content, and analyse our traffic; see our Cookie Policy.
minimax/minimax-music-2.6A whole song from one sentence, 110 F a track
Describe the style, the mood and the occasion, and it writes and performs a song up to five minutes long. Give it your own lyrics or let it write them; ask for an instrumental and it leaves the voice out. One flat price per track, whatever the length.
One price per track, up to five minutes
Write your own, or let the model write them from your prompt
Ask for no vocals and get the backing alone
Generation is a job: you poll for the finished track
Mid-tempo afrobeats, highlife guitar and a round bass, joyful chorus, the feel of a Cotonou market at first light.
Festive coupé-décalé for a drinks advert: brass, percussion, thirty seconds of energy and a sung tagline.
Instrumental only: kora and a soft pad, slow tempo, for the opening of a podcast about farming.
West African gospel, four-part choir, organ and drums, hopeful lyrics in French.
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-2.6",
"prompt": "Afrobeats, warm bass, talking drum, 100 BPM, a chorus that stays with you"
});
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-2.6`).
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.