WOW thank you for all the great feedback! adding a bunch of this stuff to my backlog right now. glad you’re having fun!
A member registered Aug 06, 2018 · View creator page →
Creator of
Recent community posts
itch.io Community » General » Release Announcements · Created a new topic klattsch: a fun retro speech synthesizer that can talk and sing
klattsch - a retro vocal synth that talks and sings
klattsch is a retro vocal synthesizer for desktop and Android. It’s built on the kind of formant speech synthesis that made computers talk in the 1980s, so it doesn’t sound smooth or human. It sounds strange, buzzy, and stiff, but eerily alive, and with a little practice it can talk, sing, and make sounds you’ve never heard come out of a computer.
Get it on itch.io - $4.99, free demo on the listing.
If the name is familiar: I made the original klattsch web toy, the one that went around. It’s still free in your browser at klatts.ch. This is the full app version with a piano roll and a bunch of other stuff.
What it does
Type something and hear it speak. Then bend the pitch, stretch the timing, and shape the voice until it’s singing a melody or muttering like a haunted answering machine.
- Type plain English and klattsch sounds it out phoneme by phoneme.
- Write in Japanese kana or romaji and it speaks that too.
- Drop into raw ARPABET phoneme codes for total control over every sound.
- Give words a melody with notes, pitch glides, vibrato, and tremolo.
- Sculpt the voice with breathiness, spectral tilt, vocal effort, and formant scale.
Also, there’s a friend that lives in there.
Make it sing
Switch to the piano roll and draw notes directly. Place syllables on a grid, set their pitch and length, and build a full vocal line. Multiple voice parts let you write harmonies and chords.
Export a video to share anywhere, with an optional karaoke-style highlight that follows along as it sings. Export lossless WAV to keep or reuse. Import a backing track and sing over it.
What you get
The itch.io version is the full, DRM-free build. Everything is unlocked, forever. One purchase covers the desktop app (Windows, Linux, Mac), the Android APK, and every future update. It works entirely offline, never tracks you, and everything you make stays on your device. The interface is available in English, Japanese, Korean, Spanish, Portuguese, Traditional Chinese, German, French, Thai, and Indonesian.
Free desktop demos are on the listing if you want to try it first.
Come say hi
People have made genuinely wonderful things with klattsch. covers, original songs, sound design, videos. There’s a pile of them collected on klatts.ch.
The Discord has 950+ friends of klattsch in it, and it’s where I post updates and where people share what they make.
The speech synthesis engine itself is MIT-licensed and free on GitHub and npm, if you want to put it in your own project.
Whether you want to make a robot sing your favorite song, build glitchy vocal textures for a track, or just explore how synthetic speech actually works, klattsch is a playground for the human voice at its most delightfully artificial.