mirror of
https://github.com/agent0ai/agent-zero.git
synced 2026-05-23 04:17:34 +00:00
675afa8dee
Split the legacy core speech stack into two built-in, independently toggleable plugins: `_kokoro_tts` for TTS and `_whisper_stt` for STT. This refactor keeps dependency installation and bootstrap concerns in Docker/bootstrap/preload, while moving speech-specific tooling, APIs, prompts, UI, and runtime behavior into the plugins. Core now exposes engine-agnostic `tts-service` and `stt-service` brokers, with browser-native TTS preserved as the fallback when Kokoro is disabled. Included in this change: - add built-in `_kokoro_tts` plugin with plugin-owned synth API, config, status UI, and provider registration - add built-in `_whisper_stt` plugin with plugin-owned transcribe API, mic runtime, device UI, prompt injection, and provider registration - remove legacy core speech APIs/helpers/settings/UI and delete unused `webui/js/speech_browser.js` - replace the old hardcoded speech settings section with a generic voice surface backed by plugin extensions - update preload/docs/tests to match the new plugin-owned speech architecture Behavioral intent: - both plugins are built-in but not `always_enabled` - users can now hot-switch TTS and STT independently - browser TTS remains available when `_kokoro_tts` is off - Whisper mic UI only appears when `_whisper_stt` is enabled
23 lines
770 B
Python
23 lines
770 B
Python
from __future__ import annotations
|
|
|
|
from helpers.defer import DeferredTask
|
|
from plugins._whisper_stt.helpers import migration, runtime
|
|
|
|
|
|
def get_plugin_config(default=None, **kwargs):
|
|
migration.ensure_config_seeded()
|
|
return runtime.normalize_config(default or {})
|
|
|
|
|
|
def save_plugin_config(default=None, settings=None, **kwargs):
|
|
migration.ensure_config_seeded()
|
|
|
|
normalized = runtime.normalize_config(settings or default or {})
|
|
previous = runtime.normalize_config(migration.read_saved_config())
|
|
|
|
previous_model = str(previous.get("model_size") or "")
|
|
next_model = str(normalized.get("model_size") or "")
|
|
if next_model and next_model != previous_model:
|
|
DeferredTask().start_task(runtime.preload, next_model)
|
|
|
|
return normalized
|