Trillo Text is a service for extracting text from documents and media files.
Trillo Text consists of an additional microservice inside Trillo Workbench and integration with the Google Cloud Speech-to-Text service.
- Supports several file formats
- Video files – MPEG-1, MPEG-2, MPEG-4, AVI, MOV, AVCHD, H.264, and H.265, etc.
- Audio files – MP3, AAC, FLAC, OGG, WMA, etc.
- PDF files.
- Microsoft Office files – doc, docx, xls, xlsx, rtf, ppt, pptx, etc.
- Open Office files – odt, ods, odp, etc.
- Common files – xml, json, csv, txt, etc.
- Common files – xml, json, csv, txt, etc.
- Images files (using OCR) – png, jpeg, gif, tiff, etc.
- Files can be uploaded using SFTP, UI or APIs.
- Tracks each file and processes using a background job.
- Stores results in the database and makes available using API.
- Provides UI for correction.
- Includes all features of Trillo Workbench.