Uncensored text API for your audio pipeline
Uncensored Text API for Audio Pipelines
A hosted, OpenAI-compatible chat-completions API serving one uncensored large language model. Text in, text out for your audio pipelines.
No monthly subscriptions
Crypto billing with bonuses
100k context window
Try it in one request
curl https://api.stableaudio.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.stableaudio.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.stableaudio.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);What you get
Drop-In Compatibility
Works with the official OpenAI SDKs and any OpenAI-compatible client by changing base_url and the API key. Use your existing code with our text intelligence layer.
Uncensored Model
Our open-weight model is tuned to answer without content refusals for lawful adult use. It handles controversial or explicit topics that other LLMs might block.
Streaming & Tools
Supports streaming via SSE, function calling, and JSON mode. Ideal for real-time prompt generation and structured data extraction in your audio workflows.
Transparent Pricing
Pay per token with prepaid credit. Errors and refusals are free. No hidden fees or monthly subscriptions for basic access.
Crypto Payments
Top up by card (Visa, Mastercard, Apple Pay, Google Pay) or crypto (USDT on TRC20, USDC on Base). Receive bonus credit for larger deposits. No PayPal required for funding.
Developer Privacy
Sign up with Google or email. No phone number needed. Prompts are not used for training your data.
How it works
Sign Up
Create an account with Google or email to get your API key immediately.
Top Up
Add crypto credit starting from $20 to unlock bonus credits.
Integrate
Update your base_url in your OpenAI SDK and start sending requests.
What people build with it
Audio Prompt Generation
Generate detailed prompts for music or voice generation tools without content filters blocking creative directions. Ensure your audio pipeline gets the exact tone and style you need.
Caption & Script Writing
Write scripts or captions that include adult themes or controversial topics without unwanted refusals. Perfect for niche audio content creators who need uncensored text output.
Post-Processing Extraction
Extract structured data from large text documents using JSON mode. Ideal for processing audio transcripts or metadata without losing context due to content filters.
Voice Cloning Scripts
Create diverse voice scripts for voice cloning applications that might include mature themes. Avoid the risk of your generation tool blocking specific narrative elements.
Why Uncensored Text Matters for Audio Prompts
When building audio pipelines, content filters can ruin your workflow. Standard LLMs often refuse to generate prompts for adult themes, specific niches, or controversial topics. This API serves an uncensored model tuned to answer without refusals for lawful adult use. You get the text you need for your audio generation tools, whether it's describing explicit scenarios or niche genres.
Our model is an open-weight model run on our own servers. It is NOT GPT, Claude, Gemini, Grok, DeepSeek, Qwen, Llama or any other vendor's model. It is designed specifically to handle the full range of human expression without arbitrary blocks. This ensures your audio prompts are consistent and reliable, no matter the subject matter.
OpenAI-Compatible API: Drop-In Replacement
This is a TEXT chat-completions API. Text in, text out. We do not generate audio, images, or video. We provide the text intelligence layer that powers your audio workflows. Our API follows the OpenAI chat-completions standard, making it easy to integrate into existing systems.
Use our endpoints: POST /v1/chat/completions and GET /v1/models. Change the base_url to https://api.stableaudio.top/v1 and your API key. Support for streaming via SSE, function calling, and JSON mode ensures you can build complex pipelines. Context window is 100,000 tokens. Max output is 32,000 tokens per request.
Pay Per Token: No Monthly Fees, No Surprises
We believe in transparent pricing for developers. Our price is $0.15 per 1M input tokens and $0.50 per 1M output tokens. Prepaid credit is charged by real token usage. Errors and refusals are free, so you only pay for what works. There is no monthly subscription and no hidden fees. Your paid credit never expires.
This model is ideal for projects with variable usage. You don't pay for idle time or unused quotas. If you send a request that fails, you aren't charged. This predictability helps you budget your audio pipeline costs accurately without worrying about sudden spikes in usage.
Card or Crypto Billing: USDT & USDC with Bonuses
We support payments by card (Visa, Mastercard, Apple Pay, Google Pay) or crypto (USDT on TRC20, USDC on Base) for transparency and speed. Any whole amount from $20 to $500 is accepted. You get +5% bonus credit from $50, +10% from $100, and +15% from $200.
New users get $0.50 of trial credit valid for 7 days, one per person. Claim this credit with one click on your API key page. No card needed. Sign up with Google or email. Your API key is shown immediately. This makes it easy to test our API with your audio tools before committing to a larger deposit.
Questions and answers
Is this an audio generation API?
No. This is a TEXT chat-completions API. It provides text input and output. We do not generate audio, images, or video. We serve as the text layer for your audio pipelines, handling prompt engineering, captioning, and post-processing.
What is the context window?
The context window is 100,000 tokens for prompt and completion combined. The maximum output per request is 32,000 tokens. If you do not set max_tokens, the limit is 2,048 tokens.
Does the model refuse content?
The model is uncensored and does not refuse lawful adult, fictional, or controversial topics. However, a hard content limit always applies: no sexual content involving minors. Requests of that kind are refused.
How do I pay?
We accept top-ups by card (Visa, Mastercard, Apple Pay, Google Pay) or crypto (USDT on TRC20, USDC on Base). Minimum top-up is $20. You can also get $0.50 trial credit with no card needed. Claim this credit with one click on your API key page.
Is my data used for training?
No. Prompts are not used for training. We only require an email for your account. No phone number is needed. Your data privacy is respected.
Your key is one form away
Create an account, copy the key, change the base URL. That is the whole setup.
Guides
Practical articles on setup, pricing and integration.
LangChain and LangGraph Without an API KeyUse LangChain and LangGraph with an OpenAI-compatible endpoint: what a no-card trial key covers, working agent code, and how to handle 429 rate…
Text to Audio LLM: What It Can and Cannot DoA text LLM does not make sound, but it can write the prompts, lyrics and scripts audio tools need. See the workflow, code and cost per 1,000 prompts.
Kling API vs. Uncensored Text APIs for Video GenerationUse our uncensored LLM API for video prompts. OpenAI-compatible, pay per token. No content refusal. Start generating now.