| name: localai | |
| config_file: |- | |
| name: pocket-tts | |
| backend: pocket-tts | |
| description: | | |
| Pocket TTS is a lightweight text-to-speech model designed to run efficiently on CPUs. | |
| This model supports voice cloning through HuggingFace voice URLs or local audio files. | |
| parameters: | |
| model: "" | |
| # TTS configuration | |
| tts: | |
| # Voice selection - can be: | |
| # 1. Built-in voice name (e.g., "alba", "marius", "javert", "jean", "fantine", "cosette", "eponine", "azelma") | |
| # 2. HuggingFace URL (e.g., "hf://kyutai/tts-voices/alba-mackenna/casual.wav") | |
| # 3. Local file path (relative to model directory or absolute) | |
| # voice: "azelma" | |
| # Alternative: use audio_path to specify a voice file directly | |
| # audio_path: "hf://kyutai/tts-voices/alba-mackenna/casual.wav" | |
| known_usecases: | |
| - tts | |
| # Backend-specific options | |
| # These are passed as "key:value" strings to the backend | |
| options: | |
| # Default voice to pre-load (optional) | |
| # Can be a voice name or HuggingFace URL | |
| # If set, this voice will be loaded when the model loads for faster first generation | |
| - "default_voice:azelma" | |
| # - "default_voice:hf://kyutai/tts-voices/alba-mackenna/casual.wav" | |