Voice Script Helper

Step-by-step guide

1. 1
   Paste your script text
   Type or paste the text you want to prepare for text-to-speech or voiceover narration into the Input Text panel.
2. 2
   Choose your conversion options
   Enable or disable each option: expand abbreviations (Dr. to Doctor), convert numbers to words (42 to forty-two), add pause markers after punctuation, and make URLs speakable.
3. 3
   Select a pause marker style
   If pause markers are enabled, choose your format: ellipsis (...), [pause], SSML <break/> tags, or pipe (|). Match this to your TTS engine's supported syntax.
4. 4
   Click Convert for TTS
   Hit the Convert for TTS button to apply all selected transformations. The TTS-Ready Output panel shows your formatted script, ready to feed into any text-to-speech engine.
5. 5
   Copy and use in your TTS tool
   Click Copy Output to save the formatted script to your clipboard. Paste it into ElevenLabs, Amazon Polly, Google TTS, or any other voice synthesis platform.

Frequently Asked Questions

What is a voice script formatter?

A voice script formatter prepares written text for text-to-speech (TTS) engines and human voiceover narrators. It converts elements that TTS engines read incorrectly: abbreviations, numerals, URLs: into their spoken equivalents, and adds pause markers to control pacing.

What abbreviations does the tool expand?

The tool expands common English abbreviations including titles (Dr. to Doctor, Mr. to Mister, Prof. to Professor), Latin abbreviations (e.g. to for example, i.e. to that is), unit abbreviations (approx. to approximately, dept. to department), and month abbreviations (Jan. to January, Feb. to February, etc.).

Why convert numbers to words for TTS?

Many TTS engines read numerals inconsistently: '42' might be read as 'forty-two' or 'four two' depending on the engine. Converting numbers to words (forty-two) guarantees consistent, natural pronunciation across all TTS platforms.

What is SSML and when should I use the SSML break tag?

SSML (Speech Synthesis Markup Language) is a standard markup language for controlling TTS speech output. The <break/> pause marker is the SSML standard for inserting pauses. Use it when your TTS platform supports SSML input, such as Amazon Polly, Google Cloud TTS, or Microsoft Azure TTS.

How does the URL-to-speech converter work?

URLs are converted to their spoken domain name with 'dot' replacing periods. For example, https://example.com/path becomes 'example dot com'. The path is omitted to keep narration clean, which works well for most podcast and video contexts where full URLs are not needed.

Which TTS platforms is this compatible with?

The formatted output works with any TTS platform: ElevenLabs, Amazon Polly, Google Cloud Text-to-Speech, Microsoft Azure Cognitive Services TTS, OpenAI TTS, and consumer tools like Murf, Descript, and Listnr. Use the SSML break tag option for platforms that support SSML markup.

Can I use this for podcast scripts?

Yes. Podcasters use voice script formatting to ensure consistent pronunciation of sponsor names, product names, URLs, and statistics. Adding pause markers also helps maintain natural pacing when the script is read aloud or fed to a TTS voice.

Does this tool write scripts for me?

No: this tool formats existing text for TTS delivery. It does not generate script content. To write a script from scratch, use the Prompt Builder or another AI writing tool, then paste the result here to format it for voice narration.

What does the pipe (|) pause marker do?

The pipe character (|) is used as a pause marker by some TTS platforms and script writing conventions. It is less standard than SSML but supported by several AI voiceover tools. Choose the marker format that matches your specific TTS engine's documentation.