Text to Speech

Key features

• Speaks any text with the voices installed on your device, with a searchable, language-grouped voice picker.
• Fine-tune rate (0.5–2×), pitch and volume — volume directly affects what gets recorded.
• Handles long-form text by speaking sentence-sized chunks in order, with a “Part N of M” progress bar.
• Play, pause, resume and stop at any time; estimation tiles show word count and expected duration.
• Drop in a .txt or .md file (up to 2 MB) instead of typing, or drag text straight onto the input.
• Record & download a real audio file: the speech is captured from the tab into a WebM (Opus) or OGG file and verified before download.

How it works

1. 1

   Enter your text

   Type, paste, or drop a .txt/.md file. Word and character counts update as you go, and long text is chunked automatically at sentence boundaries.

2. 2

   Pick a voice and tune it

   Search the voice list, then set rate, pitch and volume to taste. Local voices work offline; online voices are labeled and need a connection.

3. 3

   Listen with full transport control

   Press Speak to start; pause, resume or stop whenever you like. Progress shows which chunk is playing out of the total.

4. 4

   Record & download the audio

   Click “Record & download audio”, follow the honest 4-step prompt (choose THIS tab and switch on “Also share tab audio”), and let the speech play out. The recording is verified non-silent, then auto-downloads with an audio preview panel.

Tips for better results

• 💡Recording happens in real time — a two-minute speech takes about two minutes to capture, and leaving the tab mid-recording stops it.
• 💡Use Chrome or Edge for the download feature; other browsers may not support tab audio capture, and the tool will tell you honestly.
• 💡Lower the rate slightly for presentations or learning material — clarity beats speed for narration.
• 💡If your chosen voice sounds robotic, try another one: voice quality varies a lot between browsers and operating systems.
• 💡The volume slider changes the recorded output level, so set it before recording rather than boosting afterwards.

Frequently asked questions