YERE
DOCS_INIT // v1.0.4

Developer Documentation

Integrate sovereign African language models—Whisper, M2M-100, and MMS-VITS—directly into your applications via our low-latency local compute APIs.

API Authentication

Authenticate requests by sending your key in the header. The platform validates tokens server-side in constant time before queuing ML tasks to the air-gapped container.

HTTP Header
Authorization: Bearer yr_live_your_secret_api_key

Audio Transcription

Whisper V3

Accepts binary audio files (mp3, wav, m4a) and runs Whisper inference locally to output highly accurate text in the original language, cutting through heavy acoustic noise.

Python
import requests

url = "https://api.yere.ai/v1/transcribe"
files = {"file": open("speech.wav", "rb")}
data = {"language": "sw"}

res = requests.post(url, files=files, data=data)
print(res.json())

Text Translation

M2M-100 Core

Translates textual input from a source language to a target language. The endpoint handles cultural idioms and complex structural linguistics natively.

Javascript
const response = await fetch("https://api.yere.ai/v1/translate", {
  method: "POST",
  headers: { "Content-Type": "application/json" },
  body: JSON.stringify({
    text: "Habari gani rafiki yetu?",
    src_lang: "sw",
    tgt_lang: "en"
  })
});

const result = await response.json();
console.log(result.translated_text);

Speech Synthesis

MMS-VITS

Generates high-fidelity voicing for any language target (returns binary WAV audio stream). Neural voices are tuned specifically for indigenous tonal inflections.

cURL
curl -X POST https://api.yere.ai/v1/synthesize \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer yr_live_..." \
  -d '{"text": "Hello, welcome to Yere.", "lang": "en"}' \
  --output response_speech.wav

Model Pipeline Chaining

Unified Engine

The core execution layer. Chain L1, L2, and L3 sequentially without data ever leaving the memory state. Accepts audio, processes transcription, translates, and returns a Base64 voice response in one sub-second API call.

Python
import requests

url = "https://api.yere.ai/v1/chain"
headers = {"Authorization": "Bearer yr_live_..."}
files = {"file": open("swahili_audio.wav", "rb")}
data = {
    "src_lang": "sw",
    "tgt_lang": "en",
    "actions": "transcribe,translate,voice"
}

res = requests.post(url, headers=headers, files=files, data=data)
output = res.json()

# Returns execution logs, translated text, and base64 audio
print("Translated:", output["text_output"])