| 1 | # Kokoro TTS |
| 2 | |
| 3 | Built-in speech synthesis plugin backed by Kokoro. |
| 4 | |
| 5 | ## Behavior |
| 6 | |
| 7 | - Registers Kokoro as the active TTS provider when the plugin is enabled. |
| 8 | - Supports single voices, comma-separated equal blends, and optional in-memory weighted blends. |
| 9 | - Keeps browser-native `speechSynthesis` as the fallback path when disabled. |
| 10 | - Keeps Python dependencies on the core Docker/bootstrap path. This plugin does not install packages or binaries on demand. |
| 11 | - Uses Kokoro's existing voice-pack cache and does not create persistent blend files. |
| 12 | |
| 13 | ## Config |
| 14 | |
| 15 | - `voice`: Kokoro voice identifier or comma-separated equal blend |
| 16 | - `voice_weights`: optional mapping of voice identifiers to positive weights; when present, it defines the active blend |
| 17 | - `speed`: Kokoro playback speed multiplier |
| 18 | |
| 19 | ## Routes |
| 20 | |
| 21 | - `POST /api/plugins/_kokoro_tts/synthesize` |
| 22 | - `POST /api/plugins/_kokoro_tts/status` |