Quickstart: Integrate Uncensored Text into Your Video Workflow

Authentication & Base URL

Start by obtaining your API key from the dashboard. Our service uses standard OpenAI-compatible authentication. Set your base URL to https://api.aivideogenapi.com/v1 and pass your key in the Authorization header. This allows you to use existing video workflow tools that already support OpenAI standards without rewriting your integration logic.

• Base URL: https://api.aivideogenapi.com/v1
• Auth Header: Authorization: Bearer YOUR_API_KEY
• Model ID: uncensored

Ensure your key is active. Keys are regenerated immediately upon creation and can be revoked at any time from your account settings.

Sending a Chat Completion

Send a simple text request to generate scripts or prompts. The API accepts standard messages arrays. Since our model is uncensored, it will not refuse lawful adult, fictional, or controversial topics unless they involve minors. Use this for generating detailed video descriptions, scene directions, or metadata without safety filters truncating your creative text.

Copycurl https://api.aivideogenapi.com/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."}]
  }'

The response contains a content field with the generated text. This text can be directly passed to your video generation engine or used to populate video metadata fields.

Python SDK Integration

Use the official openai Python SDK with a custom base URL. This is the most common way to integrate our text API into video pipelines written in Python. Initialize the client with your API key and the correct base URL, then call chat.completions.create.

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.aivideogenapi.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)

This approach allows you to leverage existing Python video processing libraries while offloading the text generation to our uncensored model. You can pass system prompts to guide the tone and style of the generated video scripts.

Node.js SDK Integration

For JavaScript or TypeScript workflows, use the openai Node.js package. Configure the client with your API key and base URL just like the Python SDK. This enables seamless integration into Node-based video automation scripts.

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.aivideogenapi.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);

You can chain the output of this text generation directly into video generation API calls. The uncensored model ensures that your prompts remain intact, even if they contain mature themes or niche creative directions that standard filters might alter.

Streaming Responses

For real-time updates or large script generation, enable streaming by setting stream: true. The API returns Server-Sent Events (SSE). This is useful for building UIs that show text generation progress or for processing long video scripts in chunks without waiting for the full response.

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)

Handle the stream events in your client code to accumulate the final text. Streaming does not affect token counting or pricing; you are billed for the total tokens used in the request and completion.

Rate Limits, Errors & Context

Each API key is limited to 300 requests per minute. If you exceed this, you will receive a 429 rate limit error. The maximum request body size is 8 MB. If your API key is invalid, you will receive a 401 error. Note that credit exhaustion does not return a specific error code; it simply prevents new requests until you top up your prepaid balance.

The context window is 100,000 tokens, combining prompt and completion. This is sufficient for generating long video scripts or processing large metadata sets in a single request. If you need more context, split your input into smaller batches.