vrr/agent-zero
2
0
Fork 0
mirror of https://github.com/agent0ai/agent-zero.git synced 2026-08-25 16:25:34 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 2
agent-zero/plugins/_kokoro_tts
History
Exact
Alessandro 14b5a03e7f Enhance native Kokoro voice blending 
Bring the useful community enhancements into the built-in plugin with a current American voice catalog, speed controls, and in-memory weighted blending while preserving existing voice and speed configuration.

Reuse the singleton Kokoro pipeline, validate blend inputs, show resolved ratios in status views, and cover the native flow with focused regression tests.

Co-authored-by: twilso24 <122656888+twilso24@users.noreply.github.com>
2026-08-12 14:34:15 +02:00
..
api Refactor speech stack into built-in Kokoro TTS and Whisper STT plugins 2026-05-21 05:41:59 +02:00
extensions/webui Enhance native Kokoro voice blending 2026-08-12 14:34:15 +02:00
helpers Enhance native Kokoro voice blending 2026-08-12 14:34:15 +02:00
webui Enhance native Kokoro voice blending 2026-08-12 14:34:15 +02:00
AGENTS.md Enhance native Kokoro voice blending 2026-08-12 14:34:15 +02:00
default_config.yaml Enhance native Kokoro voice blending 2026-08-12 14:34:15 +02:00
hooks.py Refactor speech stack into built-in Kokoro TTS and Whisper STT plugins 2026-05-21 05:41:59 +02:00
plugin.yaml Enhance native Kokoro voice blending 2026-08-12 14:34:15 +02:00
README.md Enhance native Kokoro voice blending 2026-08-12 14:34:15 +02:00

README.md

Kokoro TTS

Built-in speech synthesis plugin backed by Kokoro.

Behavior

  • Registers Kokoro as the active TTS provider when the plugin is enabled.
  • Supports single voices, comma-separated equal blends, and optional in-memory weighted blends.
  • Keeps browser-native speechSynthesis as the fallback path when disabled.
  • Keeps Python dependencies on the core Docker/bootstrap path. This plugin does not install packages or binaries on demand.
  • Uses Kokoro's existing voice-pack cache and does not create persistent blend files.

Config

  • voice: Kokoro voice identifier or comma-separated equal blend
  • voice_weights: optional mapping of voice identifiers to positive weights; when present, it defines the active blend
  • speed: Kokoro playback speed multiplier

Routes

  • POST /api/plugins/_kokoro_tts/synthesize
  • POST /api/plugins/_kokoro_tts/status