Uncensored OpenAI-compatible API for developers.

VibeVoice: The Uncensored Text API for Developer Pipelines

A hosted, OpenAI-compatible chat-completions API serving one uncensored large language model designed for raw, refusal-free text output in your multimedia pipelines.

OpenAI SDK compatible
$0.25 per 1M input tokens
No content refusals

Get API key Read the docs

Try it in one request

curl 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."}]
  }'

from 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)

import 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);

$0.25per 1M input tokens

$1.00Output tokens / 1M

64,000token context

$0.50trial credit

300requests per minute

What you get

OpenAI Compatible

Works with the official OpenAI SDKs and any OpenAI-compatible client by changing base_url and the API key. Your existing code integrates with minimal friction.

Uncensored Output

The model answers without content refusals for lawful adult use, making it ideal for creative writing, script generation, and post-processing where general models might block creative or mature topics.

Code-First Integration

Access the API directly via POST /v1/chat/completions. Supports streaming via SSE, function calling, and JSON mode for structured data extraction.

Generous Context Window

Handle large inputs with a 64,000 token context window. Generate up to 16,000 tokens per request for comprehensive script or document outputs.

Simple Crypto Pricing

Pay only for real token usage with prepaid credit. Top up via USDT (TRC20) or USDC (Base) with no monthly fees and no expiration.

Fast Setup

Get your API key in seconds via Google or email. No phone number required, and every new account receives $0.50 of trial credit valid for 7 days.

How it works

Get Your Key
Sign up via Google or email to receive your API key immediately.
Configure SDK
Set the base_url to https://api.vibevoice.top/v1 and your API key in your OpenAI-compatible client.
Send Requests
Make POST requests to /v1/chat/completions with the model id 'uncensored' for raw text output.

What people build with it

Prompt Generation for Suno

Generate detailed, uncensored prompts for music generation tools like Suno without worrying about content filters blocking creative directions. Feed the output directly into their API for audio creation.

Script Writing for Video

Produce raw, refusal-free scripts for video content that might include mature themes or controversial topics. Perfect for creators who need full creative control without AI moderation layers.

Data Extraction & Post-Processing

Use the API to clean, format, or extract structured data from large text inputs. The JSON mode ensures reliable parsing for downstream applications and speech synthesis tools.

Creative Writing Assistants

Build chat interfaces or writing tools that allow for unrestricted fiction and roleplay. The uncensored nature supports diverse narrative styles and adult themes without unexpected blocks.

What is VibeVoice?

VibeVoice is an independent, hosted API offering a single uncensored large language model. It is designed for developers who need reliable text generation without the content refusals common in general-purpose AI platforms. Our API serves one open-weight model tuned for lawful adult use, ensuring that creative, controversial, or mature topics are answered directly.

Unlike multi-model platforms, we focus on delivering consistent, raw text output. This makes VibeVoice ideal for pipelines where you control the post-processing or where you need to generate content for tools like Suno, ElevenLabs, or Midjourney without intermediate censorship layers. We do not generate images, audio, or video ourselves; we provide the text layer that powers them.

OpenAI SDK Compatibility

VibeVoice is fully compatible with the OpenAI protocol. You can use the official OpenAI SDKs or any OpenAI-compatible client by simply updating the base_url and API key. The base URL is https://api.vibevoice.top/v1. This means you can swap in our uncensored model into your existing workflows with minimal code changes.

The API supports standard endpoints like POST /v1/chat/completions and GET /v1/models. You can leverage features such as streaming via Server-Sent Events (SSE), function calling, and JSON mode for structured responses. The model ID to use is 'uncensored'. This compatibility ensures that your existing integrations remain robust while gaining access to an uncensored text engine.

Why Uncensored Matters for Pipelines

General AI models often apply content filters that can interrupt creative workflows, especially in script writing, roleplay, or adult-themed content generation. VibeVoice removes these barriers, allowing your pipeline to process a wider range of inputs without unexpected refusals. This is crucial for developers building tools where the user expects full creative freedom.

However, VibeVoice is not for everyone. If you need a single API that handles text, image, and audio generation, or if you require high-uptime SLAs or SOC2 certifications, this is not the right fit. We are a text-only API with a focus on flexibility and lack of censorship, not a comprehensive enterprise suite. We also do not use your prompts for training, ensuring your data remains private.

Pricing: Pay Per Token

VibeVoice uses a straightforward pay-per-token model. Input tokens cost $0.25 per 1M, and output tokens cost $1.00 per 1M. Errors and refusals are free. There are no monthly subscriptions or hidden fees. Your prepaid credit never expires, so you only pay for what you use.

Tops are accepted via cryptocurrency only: USDT (TRC20) or USDC (Base). You can top up any whole amount from $10 to $500. Bonus credit is available for larger tops: +5% from $50 and +10% from $100. No credit cards or PayPal are accepted. Every new account gets $0.50 of trial credit valid for 7 days, with no card needed to start.

Questions and answers

Is VibeVoice an official OpenAI service?

No, VibeVoice is an independent service. It is compatible with the OpenAI API format but is not owned or operated by OpenAI. We serve our own open-weight model, not GPT-4 or other OpenAI models.

What is the context window size?

The context window is 64,000 tokens, including both the prompt and the completion. You can generate up to 16,000 tokens per request, or 2,048 if max_tokens is not specified.

How do I top up my account?

Top-ups are accepted via crypto only: USDT on the TRC20 network or USDC on the Base network. Minimum top-up is $10, and maximum is $500. Credit never expires.

Does VibeVoice generate images or audio?

No, VibeVoice is a text-only API. We provide the 'uncensored' text model for chat completions. We do not offer image, audio, or video generation endpoints.

Is there a limit on requests?

Yes, there are 300 requests per minute per key and a limit of 8 concurrent requests per key. The request body size is limited to 8 MB. Each account has one active API key at a time.

Your key is one form away

Create an account, copy the key, change the base URL. That is the whole setup.

Get API key