voice_audio_multi/include/engine/community_models/kitten_tts/frontend.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

47 lines
1.9 KiB
C++

#pragma once
#include "engine/community_models/kitten_tts/assets.h"
#include "engine/framework/text/espeak_phonemizer.h"
#include "engine/framework/runtime/session.h"
#include <cstdint>
#include <optional>
#include <string>
#include <vector>
namespace engine::models::kitten_tts {
struct KittenSynthesisInput {
std::string voice_id;
std::string language_code;
std::string phonemes;
size_t normalized_text_length = 0;
std::vector<int32_t> input_ids;
std::vector<float> style;
float speaking_rate = 1.0f;
};
struct KittenFrontendSessionState {
std::string voice_id;
std::string language_code;
const KittenVoicePack *voice_pack = nullptr;
float speaking_rate = 1.0f;
};
KittenFrontendSessionState resolve_kitten_frontend_session_state(const std::optional<runtime::Transcript> &text,
const std::optional<runtime::VoiceCondition> &voice,
const KittenAssets &assets);
void validate_kitten_frontend_session_state(const runtime::Transcript &text,
const std::optional<runtime::VoiceCondition> &voice,
const KittenFrontendSessionState &state, const KittenAssets &assets);
KittenSynthesisInput build_kitten_synthesis_input(const runtime::Transcript &text,
const KittenFrontendSessionState &state, const KittenAssets &assets,
const engine::audio::EspeakPhonemizer &phonemizer);
int64_t estimate_kitten_request_tokens(const runtime::SessionPreparationRequest &request,
const KittenFrontendSessionState &state, const KittenAssets &assets,
const engine::audio::EspeakPhonemizer &phonemizer);
} // namespace engine::models::kitten_tts