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

+6
View File
@@ -555,6 +555,12 @@ std::vector<std::unique_ptr<field>> make_tts_schema(server_task & task) {
add((new field_num("seed", task.tts_inp.data.seed))
->set_desc("RNG seed for the backbone sampler and the codec/vocoder (-1 = random)"));
add((new field_num("speed", task.tts_inp.data.speed))
->set_desc("Speaking speed relative to a typical pace, for models that support it (1.0 = model default)"));
add((new field_num("loudness", task.tts_inp.data.loudness))
->set_desc("Target loudness in LUFS, for models that support it (0.0 = model default)"));
add((new field_num("n_predict", task.params.n_predict))
->set_hard_limits(-1, INT32_MAX)
->add_alias("max_tokens")