PDF import processing
How background PDF extraction works and what you see while waiting.
PDF uploads run asynchronously. You see a processing panel while Speechdash extracts readable text in the background.
Audio and video transcription
Drag & Drop
MP3, MP4, M4A, MOV, AAC, WAV, OGG, OPUS, MPEG, WMA, WMV, PDF
or
Browse filesWhat happens after upload
You use Browse files or drop a PDF on the homepage (max 20 MB).
Speechdash uploads the file and creates a document in processing state.
A processing panel appears in the reader with status updates and decorative hero avatars.
When extraction completes, markdown content replaces the panel and you can press Play.
Credits
PDF import bills by file size: 0.5 credits per started megabyte, minimum 0.5 credits. Charged when processing runs. See What uses credits.
Extraction quality
Speechdash extracts text layers from PDFs into markdown suitable for the reader. Scanned image-only PDFs may produce little or no text. See PDF import failed.
Failed imports
If extraction fails, a failed panel shows the error message. You can delete the document and retry with a searchable PDF, or save the text as a .txt or .md file and upload it.
While processing
Playback and edit mode are unavailable until processing finishes. You can navigate away; open the document again from Library when ready.