feat(tts): add Gemini audio tag rewrite
This commit is contained in:
@@ -1290,6 +1290,14 @@ DEFAULT_CONFIG = {
|
||||
"timeout": 30,
|
||||
"extra_body": {},
|
||||
},
|
||||
"tts_audio_tags": {
|
||||
"provider": "auto",
|
||||
"model": "",
|
||||
"base_url": "",
|
||||
"api_key": "",
|
||||
"timeout": 30,
|
||||
"extra_body": {},
|
||||
},
|
||||
# Triage specifier — flesh out a rough one-liner in the Kanban
|
||||
# Triage column into a concrete spec, then promote it to ``todo``.
|
||||
# Invoked by ``hermes kanban specify`` (single id or --all). Set a
|
||||
@@ -1575,6 +1583,10 @@ DEFAULT_CONFIG = {
|
||||
"gemini": {
|
||||
"model": "gemini-2.5-flash-preview-tts",
|
||||
"voice": "Kore",
|
||||
# When true, Gemini 3.1 TTS uses a hidden auxiliary-model rewrite
|
||||
# pass to insert freeform square-bracket audio tags into the TTS
|
||||
# script. Visible chat replies are unchanged.
|
||||
"audio_tags": False,
|
||||
# Optional local Markdown/text file with Gemini TTS performance
|
||||
# direction. It may include AUDIO PROFILE, SCENE, DIRECTOR'S NOTES,
|
||||
# SAMPLE CONTEXT, and either a `{transcript}` placeholder or no
|
||||
|
||||
@@ -2980,6 +2980,7 @@ _AUX_TASKS: list[tuple[str, str, str]] = [
|
||||
("approval", "Approval", "smart command approval"),
|
||||
("mcp", "MCP", "MCP tool reasoning"),
|
||||
("title_generation", "Title generation", "session titles"),
|
||||
("tts_audio_tags", "TTS audio tags", "Gemini TTS tag insertion"),
|
||||
("skills_hub", "Skills hub", "skills search/install"),
|
||||
("triage_specifier", "Triage specifier", "kanban spec fleshing"),
|
||||
("kanban_decomposer", "Kanban decomposer", "task decomposition"),
|
||||
|
||||
Reference in New Issue
Block a user