Uncensored text API for voice pipelines

Scripts and dialogue for XTTS voices via an LLM text API

An independent, OpenAI-compatible chat-completions API for developers building voice cloning pipelines. Get raw, uncensored text generation without content refusals interfering with your scripts.

OpenAI-compatible endpoints
No content refusals
Crypto prepaid credits

Get API key Read the docs

Try it in one request

curl https://api.xtts.cc/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.xtts.cc/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.xtts.cc/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);

$0.15per 1M input tokens

$0.50Output tokens / 1M

100,000token context

$0.50trial credit

300requests per minute

What you get

OpenAI Compatible

Works with official OpenAI SDKs and any compatible client by simply changing the base_url and API key.

Uncensored Model

An open-weight model tuned to answer without refusals for lawful adult, fictional, or controversial topics.

Streaming & Tools

Supports streaming via SSE, function calling, JSON mode, and standard parameters like temperature and top_p.

Simple Pricing

Pay only for tokens used. Errors and refusals are free. No monthly subscriptions or hidden fees.

Crypto Top-ups

Top up by crypto (USDT on TRC20, USDC on Base). Get bonus credits for larger deposits starting at $50.

Privacy Focused

Prompts are not used for training. Sign up with Google or email, no phone number required.

How it works

Get Your Key

Add Credits

Top up by crypto (USDT on TRC20, USDC on Base) to start using the API. Trial credit included for new accounts.

Integrate & Build

Use the OpenAI-compatible endpoints to generate text for your voice cloning pipeline.

What people build with it

Script Generation

Generate raw, uncensored scripts for voice cloning without content filters blocking adult or niche topics. Perfect for independent content creators.

Prompt Writing

Use the API to write and refine prompts for your voice models. Ensure the text matches your desired tone and style.

Post-Processing

Clean and format text before feeding it into your TTS engine. Extract specific data or rewrite content as needed.

Captioning

Generate captions for video content that might contain mature themes. Avoid censorship issues common in standard APIs.

Why Text Matters for Voice Cloning

Most voice cloning APIs focus on generating audio, but the quality of your output depends heavily on the text input. If your text generation layer blocks adult, fictional, or controversial topics, your voice pipeline will feel limited and artificial. We provide an uncensored LLM API specifically designed for developers who need raw text for their voice models. Our model does not refuse lawful adult content, ensuring your scripts are exactly what you intended.

Unlike general-purpose chatbots, our API is optimized for text generation tasks relevant to voice pipelines. You get full control over the text, from prompt writing to post-processing, without unexpected refusals interrupting your workflow. This is critical for creators who need consistent, unfiltered text to drive their voice cloning applications.

Uncensored Text Generation

Our model is an open-weight large language model run on our own servers, tuned to answer without content refusals. It is not GPT, Claude, Gemini, or any other vendor's model. It is designed to handle lawful adult, fictional, security-research, or controversial topics without filtering. The only hard limit is that sexual content involving minors is always refused.

This means you can generate scripts for adult voice cloning, create fictional narratives with mature themes, or extract data from controversial texts without the API saying 'I can't do that' for no good reason. It is a pure text-in, text-out service. We do not generate audio, images, or video ourselves; we provide the text layer that powers your pipeline.

OpenAI SDK Compatibility

We use the standard OpenAI chat-completions format. This means you can use the official OpenAI SDKs for Python, Node.js, and other languages, or any client that speaks the OpenAI protocol. You only need to change the base_url to https://api.xtts.cc/v1 and set your API key.

Endpoints: POST /v1/chat/completions and GET /v1/models.
Model ID: Use 'uncensored' for your requests.
Features: Streaming via SSE, function calling, JSON mode, and standard parameters like temperature, top_p, and stop sequences.

This compatibility makes integration fast. You do not need to write custom parsers or handle proprietary protocols. Just plug in your key and start generating text.

Pricing & Prepaid Credits

We charge $0.15 per 1M input tokens and $0.50 per 1M output tokens. You pay only for real token usage. Errors and refusals are free. There is no monthly subscription or tiered pricing. Your prepaid credit never expires.

Top-ups are by crypto (USDT on TRC20, USDC on Base). You can add any whole amount from $20 to $500. Deposits of $50 or more get a 5% bonus, and $100+ gets a 10% bonus.

Who this is NOT for: If you need SLA guarantees, SOC2/HIPAA certifications, on-prem deployment, or audio/image generation, this is not for you. We are a simple, uncensored text API for developers who need raw data without corporate overhead.

Questions and answers

Is this API really uncensored?

Yes, our model is tuned to answer without refusals for lawful adult, fictional, or controversial topics. The only hard limit is that sexual content involving minors is always refused. It is not GPT or Claude, but an open-weight model designed for raw text generation.

Can I use the OpenAI SDK?

Yes, our API is fully OpenAI-compatible. You can use the official OpenAI SDKs by changing the base_url to https://api.xtts.cc/v1 and setting your API key. It supports streaming, function calling, and JSON mode.

How do I pay for the API?

We accept top-ups by crypto (USDT on TRC20, USDC on Base). You can top up from $20 to $500. We offer bonus credits for larger deposits.

Do I need a credit card for the trial?

No, you do not need a credit card for the trial. New users get $0.50 of trial credit, one per person, valid for 7 days. Claim this credit with one click on your API key page. You can sign up with Google or email.

What is the context window size?

The context window is 100,000 tokens for prompt plus completion together. There is no separate output cap, and if max_tokens is not set, the response can run to the end of the window.

Your key is one form away

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

Get API key Read the docs

Guides

Practical articles on setup, pricing and integration.

TTS API Demo: Live Request and Response ExamplesA hands-on tts api demo: copy-paste curl, streaming and tool-call requests with the exact response shape. Note that this API returns text, not…

TTS API Free: What the $0.50 Trial Covers (Text Only)Looking for a tts api free of charge? This service is text only, but a $0.50 trial needs no card. See exactly how many script requests that credit…

TTS API Python: Prepare Text for Speech with the SDKUsing a tts api python workflow? This endpoint is text only: see how to call it from Python to write, clean and chunk speech scripts for your…

Voice Cloning API, explained for developersExplore our OpenAI compatible TTS API for voice cloning. Pay per token for high-quality text-to-speech. Start generating audio today.

All guides →