DEVELOPER PORTAL & QUICKSTART
Integrate Ollalink in 3 lines of code.
100% OpenAI SDK-compliant gateway routing with dedicated raw GPU streaming endpoints. Zero proprietary client libraries required.
Base Endpoints & Authentication
Ollalink divides execution between general text/language gateways and specialized speech GPUs.
Gateway API
ai.ollalink.com
Used for Chat completions, RAG retrieval, Translation, and Multimodal Vision parsing.
# Base URL: https://ai.ollalink.com/v1
# Header: Authorization: Bearer sk-partner-XXXX
# Health: GET https://ai.ollalink.com/healthz
# Header: Authorization: Bearer sk-partner-XXXX
# Health: GET https://ai.ollalink.com/healthz
Speech GPU
gpu-*.ollalink.com
Direct compute access for 50-voice TTS, Voice Cloning, Whisper ASR, and WebSocket streams.
# Host: https://gpu-blr1.ollalink.com/v1
# Header: X-NH-GPU-Key: nhgpu_XXXX
# Protocol: REST (Opus) or WebSocket (PCM)
# Header: X-NH-GPU-Key: nhgpu_XXXX
# Protocol: REST (Opus) or WebSocket (PCM)
Quickstarts by Language
Python (OpenAI SDK)
from openai import OpenAI
client = OpenAI(
base_url="https://ai.ollalink.com/v1",
api_key="sk-partner-XXXXXXXXXXXX"
)
response = client.chat.completions.create(
model="chat",
messages=[{"role": "user", "content": "What is the administrative distance of OSPF in Cisco IOS?"}],
max_tokens=200
)
print(response.choices[0].message.content)
Node.js / TypeScript
import OpenAI from "openai";
const openai = new OpenAI({
baseURL: "https://ai.ollalink.com/v1",
apiKey: "sk-partner-XXXXXXXXXXXX"
});
const completion = await openai.chat.completions.create({
model: "chat",
messages: [{ role: "user", content: "Explain VLAN tagging (802.1Q)." }],
max_tokens: 250
});
console.log(completion.choices[0].message.content);
Interactive Developer Tools
Voice Quality Survey
Live rating application evaluating all 50 loudness-normalized voices across English, Hindi, and Kannada.
Launch Survey →Voice Audition Tool
Internal catalog player with self-hosted Lato typography and filterable voice metadata.
Launch Audition Tool →