We use cookies to enhance your experience, provide personalised content, and analyse our traffic; see our Cookie Policy.
elevenlabs/eleven-v4Speech at 175.596 credits per 1,000 characters
Eleven v4 is ElevenLabs' most expressive text-to-speech model: 90+ languages, including French, English, Swahili, Hausa and Yoruba, and audio tags such as [laughs] placed in the text to perform a laugh.
[laughs] and other acting cues, in the text: the voice acts out the emotion
Including French, English, Swahili, Hausa and Yoruba
The same voices across the ElevenLabs range
Billed per character: 175.596 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": "eleven-v4",
"input": "Hello, world!",
"voice": "george",
"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. `eleven-v4`).
inputRequiredThe text to synthesize.
voiceRequiredOne of this model's 21 preset voices, e.g. `george`. Any other value is refused with a 400, free of charge.
response_format"mp3"Audio container format.