Voice and emotion control
Choose an AI voice, then apply emotion presets — happy, sad, calm, neutral, and more — and adjust speed, pitch, and volume to match the tone.
Convert text and documents into natural-sounding speech
Paste your text or upload a document — TXT, PDF, DOCX, PPTX, or VTT — or even an image with OCR. Choose an AI voice, set the emotion, speed, pitch, and volume, then generate and download a natural voiceover. Built for long-form scripts and documents.
30AI voices
80+languages
200Kcharacters per run
Text to Speech
Convert text and documents into natural AI voiceovers.
Open full workspace2 credits per minute.
What this tool is built for
Convert text and documents into natural AI voiceovers.
Paste your text or upload a document — TXT, PDF, DOCX, PPTX, or VTT — or even an image with OCR. Choose an AI voice, set the emotion, speed, pitch, and volume, then generate and download a natural voiceover. Built for long-form scripts and documents.
Highlights
Built for Text to Speech
Multiple input sources
Paste text, upload TXT, PDF, DOCX, PPTX, or VTT documents, or drop in an image and pull the text out with OCR.
Built for long documents
Process articles, scripts, PDFs, and slide decks in one run — ideal for narration, study material, and business voiceovers.
How it works
How Text to Speech works
Add your content
Paste text or upload a document, VTT file, or image.
Choose voice settings
Pick a voice and fine-tune emotion, speed, pitch, and volume.
Generate and download
Generate the voiceover, preview the result, then download the audio.
Capabilities
What it handles well right now
Convert pasted text or documents to speech with natural AI voices
Import from TXT, MD, PDF, DOC, DOCX, PPTX, and VTT, or extract text from images with OCR
Set emotion presets and fine-tune speed, pitch, and volume
Handle long-form content up to 200,000 characters and download as MP3
Common jobs
What people use Text to Speech for
Video and podcast voiceover narration
E-learning and course audio content
Document and article narration
Accessibility audio versions of written content
FAQ
What people usually ask before they run it
What input types are supported?
Direct text input, document uploads (TXT, MD, PDF, DOC, DOCX, PPTX, VTT), and image uploads with OCR, so you can convert text from many sources into speech.
Can I control speed, pitch, and volume?
Yes. You can fine-tune speed, pitch, and volume, plus apply emotion presets such as happy, sad, calm, and neutral to match your use case.
Can I convert long documents to speech?
Yes. It handles long-form content such as articles, scripts, PDFs, DOCX files, and slide decks, up to 200,000 characters per run.
Should I use text to speech or subtitle to speech?
Use text to speech for plain text, long documents, and general voiceovers. Use subtitle to speech when you need VTT subtitle timing and cue-by-cue control.
How much does it cost?
2 credits per minute of generated audio.