Script to Voice Generator

Turn author scripts into fully voiced audio files - make audio books, customized one-liner packs for games, in-game dialogue lines, meditation audios, and anything else you can think of!

Description

Script to Voice Generator (STVG) converts formatted .txt or .mdscript files written by you into fully voiced audio files using Microsoft Edge-TTS — 300+ voices, unlimited, no extra costs, no API keys needed.

Its a very simple format that is easy to grasp in seconds:

Alice: Hey, can you hear me alright?
Bob: Loud and clear. How does it sound on your end?
Alice: Pretty good actually. The voices are distinct.
Bob: Great. I think we are done here

At its simplest, its just a text file where each line is essentially 'SpeakerName: What they say.'

For the advanced user, the standardized format syntax supports a lot more! Comments, pauses, emphasis, sound effect embeds, loop sound embeds, inner thoughts and many other things that even a professional VA would be excited about.

Look at this extended example script here to see the full power:
https://pastebin.com/rc7z8jCP

You can feed hundreds of lines into the program like those and it will bake you a full audio experience, including individual clips and merged audios with smart pauses to make it sound more natural and well paced than your typical raw Text-to-Speech results.

Each speaker in your script gets their own voice, pitch, speed, and audio effects. 

Assign Radio Filter, Reverb, Distortion, Telephone, Robot Voice, Cheap Mic, Underwater, Megaphone, Worn Tape, Intercom, Alien Voice, or Cave effects per character at Off / Mild / Medium / Strong levels. 

Two bonus toggles — FMSU (brutal digital corruption) and Reverse (speak backwards) — round out the toolkit. Combine effects freely for distinct character identities.

While Edge-TTS provides only 322 voices, the different settings can make them sounds like 10000+ different people. Edge-TTS is older pre-AI tech, but its neural-based results are still pretty dang good, though not on the same level as something like Elevenlabs' V3 TTS or Microsoft's Dragon HD or Google's Chirp 3 HD.

Still, Edge-TTS voices are pretty enjoyable to listen to nonetheless and fairly human-like, if slightly un-emotional/monotone by comparison to the latest tech - but definitely not crappy robot voice by any means! This stuff is good and is unlimited.

You can try edge-tts for free here:
https://huggingface.co/spaces/innoai/Edge-TTS-Text-to-Speech

The STVG generator produces these files for every script:

• Individual audios per each spoken line in the script, original clean version without effects.
• Individual audios per each spoken line in the script, altered with chosen audio filter effects.
• All (effects-enabled) individual audios merged into a fully edited and smartly paced audio file, not normalized. (true audio, better for media/games)
• All (effects-enabled) individual audios merged into a fully edited and smartly paced audio file, yes normalized. (even audio, better for podcasts)
• Reference .txt file with filenames, line numbers and contents that were voiced on those lines. (All produced audio files are .mp3, 48000 kHz, 48 or 64 kbps)

STVG's Features:

• 300+ Edge-TTS neural voices (English and multilingual)
• Per-character voice, pitch, speed, volume, and audio effects
• 12 audio effects with 4 levels each — combinable
• 2 bonus toggles: FMSU (brutal corruption) and Reverse (backward speech)
• Yell Impact mode for punchy single-word exclamations
• Inner thoughts filter (Whisper, Dreamlike, Dissociated presets)
• Sound effect events (play/stop/loop) placed in the merge timeline
• Smart merged audio with configurable punctuation-based pause timing
• Loudness-normalized and raw merge outputs
• Per-line clip files (clean and effects) for editing flexibility
• Character profiles saved automatically between sessions
• Parse log with line-by-line error reporting
• Included example scripts and AI prompt templates to get started fast

STVG is Ideal for:

• Game dialogue
• Character oneliners
• Audio dramas
• Audio books
• Ambient narration
• Meditations audios
• Voice banks

...and any project where you want to convert a written script into audio. Its unlimited, good quality and all fully automated.

Zip package includes in-depth guides covering script writing for TTS and the full audio effects pipeline. It has everything needed to make you a pro at creating audio experiences so easily it'll blow your socks off.

---

Check out everything else I do: ✨🚀

 https://linktr.ee/reactorcore