We use cookies to enhance your experience, provide personalised content, and analyse our traffic; see our Cookie Policy.
google/gemini-3.8-flash-lite-ttsSpeech at 38 credits per 1,000 characters
Google's Gemini text-to-speech model, with 30 voices. Answers WAV (24 kHz, 16-bit mono) or raw PCM.
Thirty named voices, from Kore to Sulafat
WAV (24 kHz) or raw PCM, ready to play or to feed an audio pipeline
Checked on French and English text
Billed per character: 38 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": "gemini-3.8-flash-lite-tts",
"input": "Hello, world!",
"voice": "Kore",
"response_format": "wav"
});
const buffer = Buffer.from(await response.arrayBuffer());
fs.writeFileSync('speech.wav', 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. `gemini-3.8-flash-lite-tts`).
inputRequiredThe text to synthesize.
voiceRequiredOne of this model's 30 preset voices, e.g. `Kore`. Any other value is refused with a 400, free of charge.
response_format"wav"Audio container format. This model answers `wav` (the default) or raw 24 kHz `pcm` only; any other value is refused with a 400, free of charge.