mtmd: add zonos3-mini TTS model (#32020)

* zonos3 init

* add audio gen pipeline

* fix string_format

* add default voice as gguf metadata

* better ref

* support voice clone

* add delivery params

* optimize speed

* nits

* nits 2

* add text normalization

* nits
This commit is contained in:
Xuan-Son Nguyen authored and GitHub committed 2026-11-15 19:44:44 +01:00
1 parent f4d0673917
commit 7ae3c6b231
38 files changed
+3532 -100

No files matched your search

-4
View File
@@ -799,10 +799,6 @@ json convert_speech_to_tts(const json & inp_body) {
throw std::invalid_argument("Only 'audio' stream_format is supported for speech");
}
if (json_value(inp_body, "speed", 1.0) != 1.0) {
throw std::invalid_argument("'speed' is not supported for speech");
}
if (!json_value(inp_body, "instructions", std::string()).empty()) {
SRV_WRN("%s", "'instructions' is not supported for speech and is ignored\n");
}