Generation-time options for advanced TTS synthesis.
More...
#include <cxx-api.h>
Definition at line 1016 of file cxx-api.h.
◆ extra
| std::unordered_map<std::string, std::string> sherpa_onnx::cxx::GenerationConfig::extra |
Model-specific extra attributes serialized to JSON internally.
Definition at line 1033 of file cxx-api.h.
◆ num_steps
| int32_t sherpa_onnx::cxx::GenerationConfig::num_steps = 5 |
Number of flow-matching steps when supported.
Definition at line 1030 of file cxx-api.h.
◆ reference_audio
| std::vector<float> sherpa_onnx::cxx::GenerationConfig::reference_audio |
Reference audio samples for zero-shot or voice-cloning models.
Definition at line 1024 of file cxx-api.h.
◆ reference_sample_rate
| int32_t sherpa_onnx::cxx::GenerationConfig::reference_sample_rate = 0 |
Sample rate of reference_audio.
Definition at line 1026 of file cxx-api.h.
◆ reference_text
| std::string sherpa_onnx::cxx::GenerationConfig::reference_text |
Optional reference text. Not all models require it.
Definition at line 1028 of file cxx-api.h.
◆ sid
| int32_t sherpa_onnx::cxx::GenerationConfig::sid = 0 |
Speaker ID for multi-speaker models.
Definition at line 1022 of file cxx-api.h.
◆ silence_scale
| float sherpa_onnx::cxx::GenerationConfig::silence_scale = 0.2 |
Silence scale between sentences.
Definition at line 1018 of file cxx-api.h.
◆ speed
| float sherpa_onnx::cxx::GenerationConfig::speed = 1.0 |
Speech speed. Used only by some models.
Definition at line 1020 of file cxx-api.h.
The documentation for this struct was generated from the following file:
Collaboration diagram for sherpa_onnx::cxx::GenerationConfig:
