Read Aloud and PDF to audiobook
Turn a pdf to audiobook or any document into spoken audio — Read Aloud makes an MP3, Document to Audiobook makes a chaptered M4B, all on-device.
PDF to audiobook conversion is two clicks in 1FileTool: drop the document on AI Tools › Document to Audiobook and you get a chaptered M4B that plays in any audiobook app, or pick Read Aloud for a plain MP3 of a document or text. Speech is generated on-device — once a voice is downloaded, no internet is involved.
Protect your originals first
Replace source is ON by default: the output overwrites the original file and no backup is kept. Before following along, open Settings › General and turn Replace source off, or pick a separate output folder.
Audio files are written as new files in your output folder; the source document is never changed.
The two tools
| Tool | Input | Output |
|---|---|---|
| Read Aloud | PDF, Markdown or plain text | MP3 speech — "Turn a document or text into natural speech (MP3)" |
| Document to Audiobook | PDF or Markdown | M4B with chapter markers, or MP3 — "PDF or Markdown to a chaptered M4B audiobook" |
Both live under AI Tools. Drop the document, pick a voice, run — the audio file lands in your output folder.
Voices
Voices are Piper models that download once (roughly 60–120 MB each) and then run entirely offline:
| Voice | Accent | Size | Note |
|---|---|---|---|
| Lessac | US English | ~63 MB | Recommended default |
| Amy | US English | ~63 MB | |
| Alan | British English | ~63 MB | |
| Ryan | US English | ~121 MB | Highest quality, slower to generate |
Pick the voice once per run; the model stays on disk for the next one.
Format and chapters
Document to Audiobook offers an Output format choice — the app's own hint: "M4B carries chapters, MP3 plays anywhere."
- M4B gets chapter markers taken from the document's headings — Markdown
##sections or detected PDF sections — so players can skip between them. - MP3 is one flat track encoded at libmp3lame V3 quality for maximum player compatibility.
Markdown is flattened to speakable text first, so markup characters are never read aloud.
Limits
- Free plan: voices preview the first ~600 characters — enough to audition the voice before upgrading.
- Pro: full-length documents.
- Speech goes one way. There is no transcription or subtitle generation — turning audio into text is not a feature.