To be evaluated Models which will be evaluated soon. ResembleAI/chatterbox Text-to-Speech • Updated Sep 23, 2025 • 548k • • 1.46k SparkAudio/Spark-TTS-0.5B Text-to-Speech • Updated Mar 7, 2025 • 910 • 725 canopylabs/orpheus-3b-0.1-ft Text-to-Speech • 4B • Updated May 6, 2025 • 10.3k • • 660 HKUSTAudio/Llasa-3B Text-to-Speech • 4B • Updated May 10, 2025 • 470 • 525
Evaluated in v2 The TTS models that are in TTSDS2, which will be released soon. SWivid/E2-TTS Text-to-Speech • Updated Mar 12, 2025 • 96.4k • 57 SWivid/F5-TTS Text-to-Speech • Updated Mar 21, 2025 • 722k • 1.15k amphion/Vevo Text-to-Speech • Updated Apr 13, 2025 • 20 • 45 amphion/MaskGCT Text-to-Speech • Updated Apr 13, 2025 • 962 • 305
To be evaluated Models which will be evaluated soon. ResembleAI/chatterbox Text-to-Speech • Updated Sep 23, 2025 • 548k • • 1.46k SparkAudio/Spark-TTS-0.5B Text-to-Speech • Updated Mar 7, 2025 • 910 • 725 canopylabs/orpheus-3b-0.1-ft Text-to-Speech • 4B • Updated May 6, 2025 • 10.3k • • 660 HKUSTAudio/Llasa-3B Text-to-Speech • 4B • Updated May 10, 2025 • 470 • 525
Evaluated in v2 The TTS models that are in TTSDS2, which will be released soon. SWivid/E2-TTS Text-to-Speech • Updated Mar 12, 2025 • 96.4k • 57 SWivid/F5-TTS Text-to-Speech • Updated Mar 21, 2025 • 722k • 1.15k amphion/Vevo Text-to-Speech • Updated Apr 13, 2025 • 20 • 45 amphion/MaskGCT Text-to-Speech • Updated Apr 13, 2025 • 962 • 305
