tktts プログラム仕様

ai.tktts.apply_replacements(text, replacements)

置換辞書を使ってテキストを置換（大文字小文字無視）

ai.tktts.create_temp_dir(temp_dir)

ai.tktts.get_available_voices(tts_engine, endpoint=None)

ai.tktts.get_available_voices_info(tts_engine, endpoint=None)

ai.tktts.get_speaker_dict(tts_engine, dialogue, voices, default_voicevox_voice='四国めたん', default_pyttsx3_voice='Zira', default_winrt_voice='Ayumi', default_aqt_preset='れいむ', default_optnai_voice='alloy')

ai.tktts.get_tts(tts_engine)

ai.tktts.list_available_voices(tts_engine, endpoint=None)

ai.tktts.load_text(input_path, monologue=False, wait_for_clipboard=True)

入力元('clip'またはファイルパス)からテキストを取得し、(speaker, text)リストを返す

ai.tktts.normalize_speaker(speaker, tts_engine)

ai.tktts.parse_kv_string(kv_string, keys=[], allow_no_key_kv_string=False)

key=val;key=val 形式を dict に変換

ai.tktts.speak_dialogue(args, dialogue, voice_map=None, speakers={}, replacements=None, default_voicevox_voice='四国めたん', default_pyttsx3_voice='Zira', default_winrt_voice='Ayumi', default_aqt_preset='れいむ', default_optnai_voice='alloy', endpoint=None, output_format='mp3')

選択されたエンジンで音声生成・結合・保存/再生を行う

class ai.tktts.tkTTS(tts_name=None, config={})

ベースクラス: object

get_default_voice(tts_name=None)

get_speakers_from_dialogue(dialogue)

get_tts_name(tts_name)

list_available_voices(tts_name=None, endpoint=None)

load_text(input_path, monologue=False, wait_for_clipboard=True)

normalize_speaker(speaker, tts_name=None)

parse_kv_string(kv_string, keys=[], allow_no_key_kv_string=False)

key=val;key=val 形式を dict に変換

set_aquestalk_path(aquestalk_path)

set_endpoint(endpoint)

set_engine(tts_name)

show_voice_map(infile, voices, VOICE_MAPS, is_monologue, tts_name=None, endpoint=None)

speak_dialogue(dialogue=None, voice_map=None, speakers={}, replacements=None, endpoint=None, output_format='mp3', config=None)

update_voice_map(voice_map={}, voices='', speakers={})