OpenTTS: Difference between revisions
Jump to navigation
Jump to search
Synesthesiam (talk | contribs) (Added initial description) |
Synesthesiam (talk | contribs) (Fix link to MaryTTS) |
||
| Line 7: | Line 7: | ||
* Every text to speech engine and voice is available through a single HTTP API | * Every text to speech engine and voice is available through a single HTTP API | ||
* A [ | * A [[MaryTTS]]-compatible HTTP API is available, allowing OpenTTS to be used without custom plugins in [https://www.home-assistant.io/ Home Assistant], etc. | ||
* Basic SSML support allows mixing multiple voices with custom silence breaks and word pronunciations | * Basic SSML support allows mixing multiple voices with custom silence breaks and word pronunciations | ||
[[Category:TTS]] | [[Category:TTS]] | ||
[[Category:Project]] | [[Category:Project]] | ||
Revision as of 04:22, 17 November 2021
What is OpenTTS
OpenTTS is a collection of Docker images (one per language) with many open source text to speech engines and voices.
https://github.com/synesthesiam/opentts
Advantages
- Every text to speech engine and voice is available through a single HTTP API
- A MaryTTS-compatible HTTP API is available, allowing OpenTTS to be used without custom plugins in Home Assistant, etc.
- Basic SSML support allows mixing multiple voices with custom silence breaks and word pronunciations