Generate speech locally
Piper turns text into speech on your own device, so it can work well for offline narration, assistants, and accessibility tools.
LOCAL TEXT-TO-SPEECH VOICE MODELS
Piper text-to-speech voice models
Browse Piper models for generating speech locally from text. Each listing links to the source where the model and its supporting files were published.
Browse Piper voice models →- Voice models
- 2
- Creators
- 2
- Working links
- 100%
PIPER MODEL DIRECTORY
Browse Piper voice models
Showing 2 of 2 · Page 1 of 1
H
▮ ▮ ▮ ▮ ▮
Piper·Language unverified
Homer
Standalone artifact
by bibebobberson
Speaking
View modelDownload and source details→
PV
▮ ▮ ▮ ▮ ▮
Piper·Language unverified
Piper V1
Standalone artifact
by LocomotivePlayz
Speaking
View modelDownload and source details→
EXPLORE RELATED PAGES
Voices and ways to narrow this directory
Continue by voice, framework, language, franchise, category, or creator when that context is represented in these models.
BEFORE YOU DOWNLOAD
How to choose a Piper model
Start with what you want to make: live voice changes, recorded speech, a song cover, or another vocal project. Then check the model's language, version, files, and app requirements.
Check the model version
Different versions of the same framework may need different tools or settings.
Check the language
Do not assume a model's language from the character name alone.
Check what is included
Look for the required weights, configs, checkpoints, setup notes, demos, and app requirements.
Common questions
Does AIVoices host these models?
No. Each listing links to the external page where the model was published.
Why can the same voice appear more than once?
Different creators, datasets, framework versions, and training runs remain separate models.
What can you use Piper voices for?
Piper is a lightweight text-to-speech system designed to run locally. Its voices generate speech from text rather than converting an existing performance, making them useful for narration, assistants, accessibility, and offline applications.
Before you download
Check the original source for the voice model, matching configuration file, supported language, sample rate, license, and setup instructions.
PIPER VOICE BASICS
Choose a Piper voice for your project
Start with the language and voice you need, then check the model quality, sample rate, required configuration, and license.
Keep the model and config together
A Piper voice normally needs its model file and matching JSON configuration. Download the complete voice package described by the source.
Languages and quality levels vary
Piper voices are trained for specific languages and may be released at different quality levels. Check the listing and original model card before choosing one.