Prompts and scripts over one endpoint

Base URL & Authentication

Use the base URL https://api.stableaudio.top/v1 with any standard OpenAI-compatible client. Pass your API key in the Authorization header as Bearer YOUR_API_KEY. You can generate a key instantly on the Get API key page using Google or email + password. Each account supports one active key; issuing a new one replaces the previous key. The endpoint supports POST /v1/chat/completions and GET /v1/models only. No embeddings, image, audio, or video generation is available here. This is a text-only layer for your audio pipeline.

Send Your First Request

Send a standard chat completion request to generate text. The model ID is uncensored. It is an open-weight model tuned for fewer content refusals on lawful adult topics. You can adjust parameters like temperature and top_p. The model has a 100,000-token context window. You can request up to 32,000 tokens per response. Pricing is transparent: $0.15 per 1M input tokens and $0.50 per 1M output tokens. Errors and refusals do not consume credit.

Copycurl 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."}]
  }'

Python SDK Integration

Use the official OpenAI Python SDK to integrate the API into your Python scripts. Set the base_url and api_key in your client configuration. This allows you to leverage existing codebases that already use OpenAI’s interface. The client handles JSON serialization and response parsing automatically. You can stream responses or process them in batch mode. This approach works for prompt generation, script writing, or extracting structured data from text inputs for your audio workflow.

Copyfrom 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)

Node SDK Integration

Integrate the API into your Node.js applications using the OpenAI Node SDK. Configure the client with the correct base URL and API key. This ensures compatibility with standard OpenAI patterns. You can make synchronous or asynchronous requests. Use this for real-time text processing in web hooks or background jobs. The SDK handles retry logic and response parsing. This is ideal for building voice-over scripts or captioning pipelines that require reliable, uncensored text output without subscription fees.

Copyimport 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);

Streaming Responses (SSE)

Enable streaming by setting stream: true in your request. The API returns Server-Sent Events (SSE). Token usage information is included in the final chunk. This reduces perceived latency for long text generation. Use this for live captioning or interactive prompt refinement. The model ID remains uncensored. Streaming does not change the pricing model. You still pay only for the actual tokens generated. Errors during streaming are handled gracefully without consuming extra credit.

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)

Token Limits & Quotas

The model supports a 100,000-token context window. Max output is 32,000 tokens per request, or 2,048 if max_tokens is unset. You are limited to 300 requests per minute per key. Concurrency is capped at 8 simultaneous requests per key. Request bodies must not exceed 8 MB. If you exceed the rate limit, you receive a 429 error. If your key is invalid, you receive a 401 error. If you lack sufficient prepaid credit, you receive a 402 error. Errors and refusals are free. Credit never expires. Top up by card (Visa, Mastercard, Apple Pay, Google Pay) or crypto (USDT on TRC20, USDC on Base) from $20 to $500.