Arguments for audio/TTS generation.
| 125 | |
| 126 | /// Arguments for audio/TTS generation. |
| 127 | pub struct AudioGenerationArgs { |
| 128 | /// Text to synthesize. |
| 129 | pub input: String, |
| 130 | /// Raw WAV bytes for voice cloning (from API base64 upload). |
| 131 | pub voice_data: Option<Vec<u8>>, |
| 132 | /// Path to voice prompt file (.safetensors or .wav). |
| 133 | pub voice_path: Option<String>, |
| 134 | /// Classifier-free guidance scale. |
| 135 | pub cfg_scale: f32, |
| 136 | /// Maximum speech frames to generate. |
| 137 | pub max_frames: usize, |
| 138 | /// Number of diffusion steps per frame. |
| 139 | pub diffusion_steps: usize, |
| 140 | } |
| 141 | |
| 142 | /// Output from audio generation. |
| 143 | pub struct AudioOutput { |
nothing calls this directly
no outgoing calls
no test coverage detected