I’ve created a system called OpenTTS that unifies access to multiple open source text to speech systems like:
Using docker-compose, you can get going with:
version: '2'
services:
opentts:
image: synesthesiam/opentts
ports:
- 5500:5500
command: --marytts-url http://marytts:59125 --mozillatts-url http://mozillatts:5002
tty: true
marytts:
image: synesthesiam/marytts:5.2
tty: true
mozillatts:
image: synesthesiam/mozilla-tts
tty: true
Visit http://localhost:5500 to try out different voices and TTS systems. An OpenAPI test page is available at http://localhost:5500/api/
Also check out the voice samples
This image will be updated as I find or build more voices
NOTE: The Mozilla TTS Docker image only works on amd64
(no Raspberry Pi) and does not include AVX or GPU support.