• N2 Linux無償版\|株式会社KDDI総合研究所\|

一般公開は無理そう

（６）本規約で弊社が別途許諾している場合以外に、営利・非営利に拘らず、本ソフトウェア、又は本ソフトウェアの使用により作成された音声データを、複製、頒布、貸与、譲渡、公衆送信、送信可能化若しくは上映すること（家庭内や少数の友人間など限られた範囲内で使うために行う本音声データの複製については除く。）

tar tvf n2-linux-foc-debian-amd64-1.4.15.tar.gz drwxr-xr-x root/root 0 2018-10-05 16:42 n2-linux-foc-debian-amd64-1.4.15/ -rw-r--r-- root/root 2323 2018-09-06 09:53 n2-linux-foc-debian-amd64-1.4.15/INSTALL.ja -rw-r--r-- root/root 11080 2017-07-11 23:52 n2-linux-foc-debian-amd64-1.4.15/LICENSE.ja -rw-r--r-- root/root 1691 2018-10-05 16:42 n2-linux-foc-debian-amd64-1.4.15/README.ja -rw-r--r-- root/root 2976 2018-10-05 10:30 n2-linux-foc-debian-amd64-1.4.15/libn2tts1-dev_1.4.15-1_amd64.deb -rw-r--r-- root/root 233374 2018-10-05 10:30 n2-linux-foc-debian-amd64-1.4.15/libn2tts1-foc_1.4.15-1_amd64.deb -rw-r--r-- root/root 1795716 2018-10-05 10:30 n2-linux-foc-debian-amd64-1.4.15/n2tts-lexicon_1.4.15-1_all.deb -rw-r--r-- root/root 2344478 2017-07-24 16:25 n2-linux-foc-debian-amd64-1.4.15/n2tts-voice-fa001_1.4.12-1_all.deb -rw-r--r-- root/root 2495526 2017-07-24 16:25 n2-linux-foc-debian-amd64-1.4.15/n2tts-voice-fa_1.4.12-1_all.deb -rw-r--r-- root/root 3642582 2017-07-24 16:25 n2-linux-foc-debian-amd64-1.4.15/n2tts-voice-fb_1.4.12-1_all.deb -rw-r--r-- root/root 3998762 2017-07-24 16:25 n2-linux-foc-debian-amd64-1.4.15/n2tts-voice-ma_1.4.12-1_all.deb -rw-r--r-- root/root 4263548 2017-07-24 16:25 n2-linux-foc-debian-amd64-1.4.15/n2tts-voice-mb_1.4.12-1_all.deb -rw-r--r-- root/root 29498 2018-10-05 10:30 n2-linux-foc-debian-amd64-1.4.15/n2tts_1.4.15-1_amd64.deb $ tar xf n2-linux-foc-debian-amd64-1.4.15.tar.gz $ sudo dpkg -i n2-linux-foc-debian-amd64-1.4.15/*.deb $ n2tts -h usage: n2tts -o output_file [-l <lexicon_file>] [-m <voice_file>] [-t <text_type>] [[-p key=value] ...] [-r samplerate] [-e <output_type>] [--] [utf8_text] n2tts -h options: -e <output_type> output type: raw, wav (default=wav) -h print this message -l <lexicon_file> lexicon file (default=/usr/share/n2tts/lexicon/lexicon.dat) -m <voice_file> voice model file (default=/usr/share/n2tts/voice/fa001.dat) -o <output_file> output file -p key=value control parameter (key: VOLUME, SPEECHRATE, PITCH, PITCHRANGE) -r <samplerate> sample rate: 8000, 16000, 32000 (default=32000) -t <text_type> input text type: plain, jeita-it-4006-kana (default=plain) environmental variables: N2TTS_LEXICONPATH lexicon search path (default=.:/usr/share/n2tts/lexicon) N2TTS_VOICEPATH voice search path (default=.:/usr/share/n2tts/voice)

$ n2tts -o - こんにちは | aplay

青空文庫読み上げ

$ wget -O - https://www.aozora.gr.jp/cards/001090/files/42307_txt_24297.zip | zcat | nkf -w | xargs -I{} -n1 sh -c "echo {}; n2tts -o - -- {} | aplay 2>/dev/null "