Uncensored Text API
OpenAI-Compatible LLM API for Transcript Post-Processing
A hosted, open-weight LLM for post-processing speech-to-text output, scripts, and captions without content filters.
- OpenAI-compatible chat completions API
- 100k token context window
- No content refusals for lawful content
Try it in one request
curl https://api.speechtotextapis.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."}]
}'from openai import OpenAI
client = OpenAI(base_url="https://api.speechtotextapis.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)import OpenAI from "openai";
const client = new OpenAI({ baseURL: "https://api.speechtotextapis.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);What you get
Direct Text Processing
Input raw ASR text and receive cleaned, scripted, or extracted output. We handle the text layer, not media generation.
Uncensored Model
Our model answers without softening lawful adult, controversial, or creative content. Minor sexual content is the only hard limit.
Standard Integration
Works with official OpenAI SDKs. Swap your base_url and API key to use our endpoint with existing client libraries.
Streaming Support
Receive text outputs via Server-Sent Events (SSE) for real-time processing in your transcription or captioning pipelines.
Function Calling
Structure your post-processed text into JSON objects using tool/function calling for automated data extraction from transcripts.
Simple Pricing
Pay-as-you-go prepaid credit. No monthly fees, no subscriptions, and credits never expire. Top-ups include bonus credits.
How it works
Sign Up
Create an account with email and password to receive your API key immediately.
Add Credit
Load prepaid credits by crypto (USDT on TRC20, USDC on Base); new accounts get $0.50 trial credit.
Integrate
Point your OpenAI-compatible client to our base URL and start processing text.
What people build with it
Transcription Cleanup
Post-process raw ASR output to fix errors, remove filler words, and format timestamps without censorship of the content.
Caption Generation
Write and clean subtitle text for video content from your existing transcripts, including adult or edge-case material that general models might block or soften.
Script Extraction
Convert long-form audio transcripts into structured scripts, outlines, or dialogue formats for creative projects.
Data Extraction
Extract specific entities, metadata, or structured data from unstructured text transcripts using function calling tools.
The Text Layer of Your Media Pipeline
Most AI platforms try to do everything: generate images, audio, and video. We focus exclusively on the text layer. If you are building a voice, video, or transcription pipeline, you need a reliable text API to script, caption, extract data, or clean up ASR output. Our API is not for generating media; it is for processing the text that describes it.
Our uncensored model ensures your transcriptions and scripts are never softened or refused for lawful adult content. This makes it ideal for creative and edge-case use cases where content filters introduce noise or refusals. You get text in, text out, with no hidden capabilities.
Why Uncensored Matters for Transcription
General AI aggregators often refuse or sanitize content that is lawful but adult, controversial, or niche. Our model is tuned to answer without content refusals for these topics. The only hard limit is sexual content involving minors, which is always blocked.
For post-processing text pipelines, this means your data remains authentic. You do not get a sanitized version of your transcript or script. This is critical for media pipelines where the content itself is the product, not the filter applied to it.
OpenAI-Compatible & Developer Friendly
Our API follows the OpenAI chat-completions standard. You can use the official OpenAI SDKs or any OpenAI-compatible client by changing the base URL and API key. We support streaming via SSE and tool/function calling for structured output.
Base URL: https://api.speechtotextapis.com/v1
Model ID: uncensored
Context window: 100,000 tokens. Limits: 300 requests per minute per key. 8 MB request body. One key per account, regeneratable at any time.
Pricing: Pay Only for What You Process
No subscriptions. No monthly fees. Prepaid credit that never expires. Input: $0.15 per 1M tokens. Output: $0.50 per 1M tokens. Top-ups start at $20. +5% bonus from $50, +10% from $100, +15% from $200. New accounts get $0.50 trial credit (7 days, no card needed). Privacy: prompts are not used for training.
Questions and answers
Is this API for generating audio or video?
No. This is a text-only API. It processes text input and returns text output. It is designed for post-processing steps in media pipelines, such as cleaning up ASR output, generating scripts, or extracting data from transcripts. It does not generate audio, images, or video.
What does "uncensored" mean?
Our model does not refuse lawful adult, fictional, security-research, or controversial topics. It answers directly without softening content. The only hard limit is sexual content involving minors, which is always blocked. It is not GPT, Claude, or any other vendor's model.
Can I use this with the OpenAI Python SDK?
Yes. The API is OpenAI-compatible. You can use the official SDKs by setting the base URL to https://api.speechtotextapis.com/v1 and providing your API key. The model ID to send is uncensored.
Do I need a credit card to start?
No. You can sign up with just an email and password. 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 add prepaid credit via crypto (USDT, USDC) later, starting at $20.
Who is this NOT for?
This is not for you if you need image generation, audio generation, video generation, embeddings, or fine-tuning. It is also not for you if you need a specific named vendor model like GPT-4 or Claude. It is strictly for text post-processing using our uncensored model.
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.
OpenAI Compatible API Key: Get One and Send a CallHow to get an OpenAI compatible API key, set the base URL and model, and send your first request with curl, Python or Node. Includes limits and fixes.
Text To Speech API: How to Use an Uncensored LLM for Voice Scripts & CaptionsUse our pay as you go LLM API for uncensored text-to-speech pipelines. Generate scripts and captions. Get your OpenAI compatible API key now.