TTS Input Text
170/10000
Voice Selection
TTS Generated Audios

Your generated audio will appear here

Enter some text on the left and click Generate to get started.
Voice Cloning Input
Voice Clone Generated Audios

Your cloned voice will appear here

Fill in the form on the left and click Clone & Generate.
Voice Design Input

Longer, detailed descriptions give better voices: age, gender, accent, pace, mood and use. Example: “a warm British woman in her 30s, slow and friendly, for audiobooks”.

Voice Design Generated Audios

Your designed voice will appear here

Describe a voice on the left and click Design & Generate.
Voice Changer Input
Voice Changer Generated Audios

Your converted audio will appear here

Fill in the form on the left and click Change Voice.
AI Dubbing Input
More options
AI Dubbing Generated Results

Your dubbed video will appear here

Choose a video on the left and click Generate Dub. The new voice replaces the original sound.
Speech to Text Input
Speech to Text Generated Results

Your transcript will appear here

Fill in the form on the left and click Transcribe.
Music Generator Input

Longer prompts give better music: genre, mood, instruments, tempo and where it will be used. Example: “calm lo-fi hip hop, soft piano, light rain, 80 bpm, for studying”.

More options
Music Generated Audios

Your music will appear here

Describe a track on the left and click Generate Music.
SFX Generator Input

Detailed prompts give better sounds: one clear sound, what makes it, the place and the distance. Example: “single wooden door knock, close up, small dry room”.

SFX Generated Audios

Your sound effect will appear here

Describe an effect on the left and click Generate SFX.
Song Generator Input

Describe the vocal, genre, instruments, tempo and mood for the best song. Example: “soft female vocal, acoustic pop, guitar and piano, 90 bpm, warm and hopeful”.

More options
Song Generated Audios

Your song will appear here

Fill in the form on the left and click Generate Song.
Lyrics Generator Input

Longer topics give better lyrics: names, places, a small story and the mood. Example: “my mom's 60th birthday, her garden, the songs she sang to us, grateful and happy”.

Lyrics Generated Results

Your lyrics will appear here

Give a topic on the left and click Generate Lyrics.
Vocal Isolator Input
Vocal Isolator Generated Audios

Your isolated vocals will appear here

Paste a track on the left and click Isolate Vocals.
Voice Cover Input

Upload a song with a clear lead vocal. It re-sings the lyrics in the new voice you pick, in the same style.

Voice Cover Generated Audios

Your voice cover will appear here

Fill in the form on the left and click Generate Cover.

Document to Audio: Turn Word and Text Files into Speech

No more copying and pasting. Open a .docx, .txt, .srt, Markdown, HTML or RTF file straight into Speechma Pro’s text box, choose one of 1,900+ voices, and download the audio as an MP3. The file is read inside your browser.

Speechma Pro

Every AI voice tool, 50 million characters a month

No ads and no security codes. $4.89 $4.40 a month, cancel any time. See what you get

In short: To turn a document into audio, open Text to Speech and press the small file button next to the character counter (or drag the file onto the text box). Speechma Pro reads Word (.docx), .txt, .srt, Markdown (.md), HTML and RTF files and puts the text in the box, up to 10,000 characters per conversion. Pick a voice, press Generate Audio and download an MP3. Longer files are converted in parts, or 10,000 characters at a time on Speechma Pro.

How to convert a document to audio

  1. Open the fileIn Text to Speech, press the file button next to the character counter (bottom right of the text box) and choose your document. Or simply drag the file from your desktop and drop it on the text box.
  2. Check the textThe words appear in the box, ready to edit. Remove anything you don’t want read aloud, like page numbers, a table of contents or a footer.
  3. Pick a voiceFilter by language and country, press play on a few voices, and choose one. Calm narration voices suit reports and study notes; brighter voices suit newsletters and scripts.
  4. Generate the audioPress Generate Audio. Your clip appears in the results list.
  5. Download MP3 or WAVPress Download for an MP3, or use the small arrow next to it to choose WAV. Results stay in your browser even if you refresh.

Which files can you open?

File typeWhat Speechma Pro readsGood to know
Word (.docx)The document textOld .doc files cannot be read. In Word, use Save As and choose .docx or .txt.
Plain text (.txt)Everything in the fileThe simplest and most reliable option.
Subtitles (.srt)Only the spoken linesCaption numbers and time codes are skipped, so you hear just the dialogue.
Markdown (.md)The text without formatting symbolsHeading marks, asterisks and backticks are removed.
Web page (.html)The visible textTags and code are left out.
Rich text (.rtf)The text without stylingHandy for files from WordPad or TextEdit.
PDFNot opened directlyOpen the PDF, copy the text and paste it into the box. See PDF to audio.

Files up to 3 MB can be opened. They are read on your own device and are not uploaded.

What about long documents?

Each conversion holds up to 10,000 characters, which is about 300 to 350 words or 2 minutes of speech. When you open a longer file, Speechma Pro loads the first 10,000 characters and tells you how long the whole file is.

For the rest, work in parts:

  1. Generate part one and download it.
  2. Copy the next section of your document (about 10,000 characters) into the box and generate again.
  3. Name the files 01, 02, 03 so they stay in order, or use “download all” to grab them as one ZIP.

A full single-spaced page is usually one to two parts.

What people turn into audio

Study notes

Listen to lecture notes and reading summaries on the bus or at the gym.

Work documents

Proofread a proposal by ear. Mistakes you skim past are easy to hear.

Subtitle files

Open an .srt and get a clean voiceover of the dialogue, without the time codes.

Newsletters and blog posts

Offer an audio version for readers who prefer to listen.

Stories and chapters

Draft an audiobook one chapter at a time. Our audiobook guide covers the full process.

Accessibility

Help people with dyslexia or low vision take in written material by ear.

Tips for a better listen

  • Delete what you don’t want spoken. Headers, footers, page numbers and long web links sound odd read aloud.
  • Turn bullet lists into sentences. Add a period at the end of each bullet so the voice pauses between items.
  • Spell out symbols. Write “percent” instead of %, and “dollars” after a number, so the voice reads it the way you expect.
  • Use the speed setting. Slightly slower speech helps with study material; slightly faster suits skimming a draft.
  • Share it straight away. On a phone, the Share button sends the audio file to WhatsApp, Telegram or email.

Frequently asked questions

How do I convert a Word document to audio?

Open Speechma Pro’s Text to Speech, press the file button next to the character counter and choose your .docx file (or drag it onto the text box). Pick a voice, press Generate Audio and download the MP3. It is included in Speechma Pro.

Can I convert a TXT file to MP3?

Yes. Open the .txt file the same way. The text loads into the box and you can download the result as MP3, or as WAV using the arrow next to Download.

Why can’t I open my .doc file?

Only the newer .docx format can be read. Open the file in Word or Google Docs, save it as .docx or .txt, and try again.

Can I convert a PDF?

PDF files cannot be opened directly. Copy the text from the PDF and paste it into the box. Our PDF to audio page explains the easiest way.

How much text can I convert at once?

Up to 10,000 characters per conversion, which is about two minutes of speech. Longer files are done in parts, or 10,000 characters at a time on Speechma Pro.

Is my document uploaded anywhere?

No. The file is read inside your browser to fill the text box. Only the text you choose to convert is sent to make the audio, and nothing is kept on our servers.
The Speechma newsletter

Make better voiceovers, faster

  • New voices and features the day they launch
  • Script templates and tricks that make AI voices sound human
  • Creator stories, community picks and early access

About twice a month, one click to leave. We never share your email. Privacy · Read past issues

Voice Effects

0
0
100%