We use cookies to enhance your experience, provide personalised content, and analyse our traffic; see our Cookie Policy.
elevenlabs/scribe-v2Transcription at 8.049 credits a minute
Scribe v2 is ElevenLabs' transcription model: 90+ languages, including French, English, Swahili, Hausa and Arabic, with word-level timestamps. Billed per second of audio.
Including French, English, Swahili, Hausa and Arabic
Timestamps for every word with verbose_json
The response names the language, for example “fra”
8.049 credits per minute, billed per second of audio
Team meeting transcription
Voice note transcription
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 result = await client.audio.transcriptions.create({
model: 'scribe-v2',
file: fs.createReadStream('audio.mp3'),
});
console.log(result.text);
console.log('Credits used:', result.tchavi.credits_used);Every parameter this model accepts on the API. Check the SDK for full typings.
modelRequiredTranscription model (e.g. `scribe-v2`).
fileRequiredAudio file to transcribe. MP3, WAV, M4A, WebM — max 25MB.
response_format"json"Shape of the transcription response.
temperature0Sampling temperature between 0 and 1. Higher values let Whisper deviate further from the most likely transcription; 0 is deterministic.
languageHint the spoken language (e.g. `fr`, `en`). Omit to auto-detect.
promptOptional context hint to bias the transcription.