We use cookies to enhance your experience, provide personalised content, and analyse our traffic; see our Cookie Policy.
mistral/voxtral-tts-3Speech at 29 credits per 1,000 characters
Mistral's text-to-speech model, with 66 preset voices. That includes a native French voice, Marie, in six moods, and four more French voices. Answers in mp3, wav, flac, opus or pcm.
Including a native French voice, Marie, in six moods, and four more French voices
mp3, wav, flac, opus or raw pcm
Preset voices tagged for 21 languages, from French and English to Arabic, Hindi and Japanese
Billed per character: 29 credits per 1,000, up to 4,096 characters per request
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';
import fs from 'fs';
const client = new Tchavi({ apiKey: 'API_KEY' });
const response = await client.audio.speech.create({
"model": "voxtral-tts-3",
"input": "Hello, world!",
"voice": "fr_marie_neutral",
"response_format": "mp3"
});
const buffer = Buffer.from(await response.arrayBuffer());
fs.writeFileSync('speech.mp3', buffer);
console.log('X-Credits-Used:', response.headers.get('x-credits-used'));Every parameter this model accepts on the API. Check the SDK for full typings.
modelRequiredTTS model (e.g. `voxtral-tts-3`).
inputRequiredThe text to synthesize.
voiceRequiredOne of this model's 66 preset voices, e.g. `fr_marie_neutral`. Any other value is refused with a 400, free of charge.
response_format"mp3"Audio container format.