voice_audio_multi/include/engine/models/personaplex/request.h
Fabio c36510c21e
Some checks failed
Linux Build / Linux cpu (push) Has been cancelled
Linux Build / Linux cpu-clang (push) Has been cancelled
Linux Build / Linux vulkan (push) Has been cancelled
mac-build / macOS CPU (push) Has been cancelled
Nix Build / Nix (cpu) (push) Has been cancelled
Nix Build / Nix (vulkan) (push) Has been cancelled
windows-build / Windows CPU (push) Has been cancelled
Initial import: audio.cpp with Orange Pi documentation
2026-11-04 19:05:22 +01:00

48 lines
1.3 KiB
C++

#pragma once
#include "engine/framework/runtime/session.h"
#include "engine/models/personaplex/assets.h"
#include <cstdint>
#include <optional>
#include <string>
#include <vector>
namespace engine::models::personaplex {
struct PersonaPlexGenerationOptions {
std::string voice_id = "NATF2";
std::optional<runtime::AudioBuffer> voice_prompt_audio = std::nullopt;
std::string system_prompt;
float temperature = 0.8F;
float text_temperature = 0.8F;
int64_t top_k = 250;
int64_t text_top_k = 250;
bool do_sample = true;
std::optional<uint32_t> seed;
};
struct PersonaPlexRequest {
runtime::AudioBuffer audio;
PersonaPlexGenerationOptions generation;
};
struct PersonaPlexVoicePromptState {
std::vector<float> embeddings;
std::vector<int64_t> cache;
int64_t frames = 0;
};
PersonaPlexRequest make_personaplex_request(
const runtime::TaskRequest & request,
const PersonaPlexAssets & assets);
PersonaPlexGenerationOptions make_personaplex_generation_options(
const runtime::TaskRequest & request,
const PersonaPlexAssets & assets);
PersonaPlexVoicePromptState load_personaplex_voice_prompt(
const PersonaPlexAssets & assets,
const std::string & voice_id);
} // namespace engine::models::personaplex