NSFW TTS API Quickstart

Python SDK

Use the official openai Python package. Set the base URL to our endpoint and provide your API key. This works seamlessly with the standard SDK because we follow the OpenAI chat-completions format exactly.

This is the fastest way to integrate the NSFW LLM API into your existing Python scripts. You do not need to parse raw JSON manually. The SDK handles the SSE streaming if you enable it, but for simple text generation, a standard call returns the full response at once.

• Install via pip install openai.
• Set base_url to https://api.nsfwttsapi.com/v1.
• Set api_key to your generated key.

Use the following snippet to generate a response.

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.nsfwttsapi.com/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 SDK

Use the openai Node.js package. Configure the client with our base URL and your API key. This allows you to use the same idiomatic code you would use for other OpenAI-compatible services.

Node developers can integrate the uncensored AI API directly into their Express or Fastify servers. The request structure is identical to the standard API. You send a messages array, and the model returns text. There is no routing noise, just direct access to the uncensored model.

• Install via npm install openai.
• Configure the client with baseURL and apiKey.
• Call chat.completions.create().

Use the following example to send a request.

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.nsfwttsapi.com/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 Responses (SSE)

Set stream: true in your request. The API returns Server-Sent Events (SSE). Each chunk contains part of the generated text. This is critical for NSFW TTS pipelines where you need to feed text to a voice engine in real-time without waiting for the full response.

Streaming reduces perceived latency significantly. You can start processing the first few tokens while the model continues to generate. The API supports this natively. Use the following code to handle the stream correctly.

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)

Context Window, Limits & Errors

The context window is 100,000 tokens for prompt plus completion. This is large enough for most NSFW TTS workflows, but keep your system prompts concise. If you exceed the limit, the API returns an error.

Rate limits are 300 requests per minute per key. The request body limit is 8 MB. Monitor your usage to avoid throttling. Common errors include 401 (invalid key), 402 (no credit), and 429 (rate limit exceeded). Pay-as-you-go credit never expires. You can top up from $10 by crypto (USDT or USDC). Bonuses apply at $50 (+5%) and $100 (+10%). A new account gets $0.50 trial credit valid for 7 days. No card is needed for the trial. This uncensored API is reliable for adult content, provided you avoid sexual content involving minors, which is always blocked.