🧠 DocAI Text to Speech

Listen instead of read, create natural AI voices, or turn audio and video into text in seconds.
DocAI Text to Speech works directly inside Google Docs™ and Slides™ with no setup required.

Turn written content into natural sounding speech, listen to documents hands free, or convert audio and video into editable text without leaving your document.

What you can do

🔊 Text to Speech and AI Voice Generator
Convert text into clear, natural sounding audio using high quality AI voices. Adjust speed, tone, pauses, emphasis, pacing, and pronunciation to create audio for documents, presentations, scripts, or videos.

🗣️ Read Aloud instantly
Select any text and have it read out loud right away. A simple way to review content, multitask, or reduce screen fatigue.

🎧 Speech to Text for audio and video
Turn audio or video into text by uploading files or pasting links. Works with YouTube videos, tutorials, screen recordings, podcasts, voice notes, and other online media.

📚 Short and long content support
Use the free tier for short requests or upgrade to process long documents, full scripts, and extended audio or video content with higher limits.

Key features

• Text to Speech with natural and premium voices
• Speech to Text for audio and video transcription
• Read Aloud for instant listening
• Multiple languages and regional accents
• Adjustable speed, tone, pauses, emphasis, and pronunciation
• Export audio as MP3, WAV, and more
• Supports up to 40K plus characters on premium plans
• Free tier included with 2 credits around 400 words total

DocAI Text to Speech brings Text to Speech, Read Aloud, AI voice generation, and Speech to Text together in one simple experience inside Google Docs™ and Slides™.