Quickstart for Vibevoice pipelines

Prerequisites and Base URL

Before starting, ensure you have an API key. Sign up via Google or email on the Get API key page to receive your key immediately. No phone number is required. You will use the official OpenAI SDKs for your preferred language. Set your base URL to https://api.vibevoice.top/v1. The model ID is uncensored. This endpoint supports standard chat completions, function calling, and JSON mode. It does not support embeddings, image generation, or audio outputs. Keep your key secure; each account allows only one active key at a time.

Sending Your First Request

Send a POST request to the chat completions endpoint. Include your API key in the Authorization header. The request body must specify the model uncensored and your messages array. The API returns structured JSON with the model's response. You can control output length with the max_tokens parameter. If omitted, the default output limit is 2,048 tokens. The context window supports up to 64,000 tokens total.

Python SDK Integration

Use the official openai Python package to interact with the API. Initialize the client with your API key and the custom base URL. Pass the model name and your system or user messages. The SDK handles serialization and error parsing automatically. This approach is ideal for backend services or data processing scripts where you need reliable, uncensored text generation for downstream tasks.

Node.js SDK Integration

Initialize the Node.js OpenAI client with your credentials and the VibeVoice base URL. Pass the required parameters to the chat.completions.create method. This method supports asynchronous execution, making it suitable for high-throughput pipelines. You can adjust parameters like temperature and top_p to control randomness. The response object contains the generated text and token usage statistics.

Streaming Responses

Enable streaming by setting the stream parameter to true. The API returns a Server-Sent Events (SSE) stream. Each chunk contains partial token data. The final chunk includes the complete token usage statistics for the request. Streaming reduces perceived latency for long-form text generation. It is useful for real-time UI updates or progressive text assembly in voice or video pipelines.

Rate Limits, Errors, and JSON Mode

The API enforces a limit of 300 requests per minute and 8 concurrent requests per key. Requests exceeding 8 MB are rejected. A 401 error indicates an invalid or missing API key. A 402 error means your prepaid credit is exhausted; top up via crypto to continue. A 429 error signals rate limiting. You can enforce structured output using response_format: {"type": "json_object"}. The model refuses sexual content involving minors, but other lawful adult content is allowed.

cURL

Copycurl https://api.vibevoice.top/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Write a blunt product review of a cheap VPN."}]
  }'

Python

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.vibevoice.top/v1", api_key="YOUR_KEY")

resp = client.chat.completions.create(
    model="uncensored",
    messages=[{"role": "user", "content": "Summarise this thread without softening it."}],
)
print(resp.choices[0].message.content)

Node.js

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.vibevoice.top/v1", apiKey: process.env.API_KEY });

const resp = await client.chat.completions.create({
  model: "uncensored",
  messages: [{ role: "user", content: "Draft a villain monologue for my game." }],
});
console.log(resp.choices[0].message.content);

Streaming

Copystream = client.chat.completions.create(
    model="uncensored",
    messages=[{"role": "user", "content": "Tell the story in second person."}],
    stream=True,
)
for chunk in stream:
    if chunk.choices and chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)