# Models to include in the leaderboard, only include models that users can vote on AVAILABLE_MODELS = { 'ElevenLabs': 'eleven', 'Play.HT 2.0': 'playht', 'MeloTTS': 'melo', 'StyleTTS 2': 'styletts2', 'Parler TTS Large': 'parlerlarge', 'Fish Speech v1.5': 'anonymousfish', 'PlayDialog': 'playdialog', 'Kokoro v0.19': 'kokoro0.19', 'CosyVoice 2.0': 'cosyvoice', # 'XTTSv2': 'xtts', # 'WhisperSpeech': 'whisperspeech', # 'OpenVoice': 'openvoice', #'OpenVoice V2': 'openvoicev2', # 'Play.HT 3.0 Mini': 'playht3', # 'MetaVoice': 'metavoice', #'GPT-SoVITS': 'sovits', # 'Vokan TTS': 'vokan', # 'VoiceCraft 2.0': 'voicecraft', #'Parler TTS': 'parler', #'Fish Speech v1.4': 'fish', } model_links = { 'ElevenLabs': 'https://elevenlabs.io/', 'Play.HT 2.0': 'https://play.ht/', 'Play.HT 3.0 Mini': 'https://play.ht/', 'XTTSv2': 'https://huggingface.co/coqui/XTTS-v2', 'MeloTTS': 'https://github.com/myshell-ai/MeloTTS', 'StyleTTS 2': 'https://github.com/yl4579/StyleTTS2', 'Parler TTS Large': 'https://github.com/huggingface/parler-tts', 'Parler TTS': 'https://github.com/huggingface/parler-tts', 'Fish Speech v1.5': 'https://github.com/fishaudio/fish-speech', 'Fish Speech v1.4': 'https://github.com/fishaudio/fish-speech', 'GPT-SoVITS': 'https://github.com/RVC-Boss/GPT-SoVITS', 'WhisperSpeech': 'https://github.com/WhisperSpeech/WhisperSpeech', 'VoiceCraft 2.0': 'https://github.com/jasonppy/VoiceCraft', 'PlayDialog': 'https://play.ht/', 'Kokoro v0.19': 'https://huggingface.co/hexgrad/Kokoro-82M', 'CosyVoice 2.0': 'https://github.com/FunAudioLLM/CosyVoice', 'MetaVoice': 'https://github.com/metavoiceio/metavoice-src', 'OpenVoice': 'https://github.com/myshell-ai/OpenVoice', 'OpenVoice V2': 'https://github.com/myshell-ai/OpenVoice', 'Pheme': 'https://github.com/PolyAI-LDN/pheme', 'Vokan TTS': 'https://huggingface.co/ShoukanLabs/Vokan', } closed_source = [ 'ElevenLabs', 'Play.HT 2.0', 'Play.HT 3.0 Mini', 'PlayDialog', ] # Model name mapping, can include models that users cannot vote on model_names = { 'styletts2': 'StyleTTS 2', 'tacotron': 'Tacotron', 'tacotronph': 'Tacotron Phoneme', 'tacotrondca': 'Tacotron DCA', 'speedyspeech': 'Speedy Speech', 'overflow': 'Overflow TTS', 'anonymoussparkle': 'Anonymous Sparkle', 'vits': 'VITS', 'vitsneon': 'VITS Neon', 'neuralhmm': 'Neural HMM', 'glow': 'Glow TTS', 'fastpitch': 'FastPitch', 'jenny': 'Jenny', 'tortoise': 'Tortoise TTS', 'xtts2': 'Coqui XTTSv2', 'xtts': 'Coqui XTTS', 'openvoice': 'MyShell OpenVoice', 'elevenlabs': 'ElevenLabs', 'openai': 'OpenAI', 'hierspeech': 'HierSpeech++', 'pheme': 'PolyAI Pheme', 'speecht5': 'SpeechT5', 'metavoice': 'MetaVoice-1B', }