getTxt.AI is an API that extracts text and markdown from documents, audio files, images, and videos through a single endpoint. Built by 4vor4 UG, it is designed for developers and teams who need to convert unstructured content into usable text for AI applications, LLM pipelines, search indexing, or document processing workflows.
Key Capabilities
- Multi-format text extraction: Supports PDF, DOCX, XLSX, PPTX, TXT, RTF, EPUB, HTML documents; MP3, WAV, M4A, FLAC audio files; MP4, AVI, MOV, WMV, MKV videos; and JPG, PNG, TIFF, BMP images through one unified API.
- Built-in summarization: Returns both short and long summaries of extracted content within the same API call, eliminating the need for separate summarization services.
- Translation support: Translates extracted text into over 50 languages in a single request, enabling cross-language document processing without additional integration.
- Markdown output: Converts extracted text to markdown format for use in documentation, note-taking apps, or content management systems.
- Multi-language OCR: Extracts text from documents and images in over 50 languages, with handwritten text recognition available for major languages including English, Chinese, French, German, Italian, Japanese, Korean, Portuguese, Spanish, Russian, and Arabic.
- Batch processing: Processes up to 10 documents per API request, with support for mixed file types in the same batch.
How It Works
The API accepts document URIs as input and returns extracted text, word counts, credit usage, and optional summaries and translations in a JSON response. Authentication uses an API key passed via the x-api-key header. Files must be directly accessible via URL with a maximum size of 100 MB for audio and video, and 500 MB or 2000 pages for documents. Image dimensions must be between 50x50 and 10,000x10,000 pixels.
Pricing
getTxt.AI operates on a credit-based pay-as-you-go model with no subscriptions or recurring fees. Each document processed consumes one credit. Free credits are provided on signup for testing, and additional credits can be purchased as needed with larger packages offering discounted rates.
Intended Users
- Developers building AI applications or LLM chains that need text extraction from multiple file formats through a single API.
- Teams processing document archives, research papers, or media files for search indexing and content analysis.
- Content creators and students who need transcription, summarization, or translation of audio and video files.
- Organizations handling international documents that require combined extraction and translation workflows.
Privacy and Security
Files uploaded to getTxt.AI are processed securely and automatically deleted after conversion. The service uses Firebase, OpenAI, Anthropic, Microsoft Azure, and AWS for processing. Payment data is handled through Stripe. Chat history is retained for 30 days and usage logs for 90 days.
