List your company

Text-to-Speech on InstructTTSEval ZH

89APSGemini-pro
27.234443.269759.30575.3403Dec 29, 2025Jan 14, 2026Jan 31, 2026Feb 17, 2026Mar 6, 2026Mar 23, 2026Apr 9, 2026

Evaluation results

MethodLinks
Gemini-pro2026.018990.175.5—
Gemini 2.5-ProCommercial=true2026.018990.175.584.8
Gemini-flash2026.0188.290.977.3—
Gemini 2.5-FlashCommercial=true2026.0188.290.977.385.4
Qwen3TTS-12Hz-1.7B-VDSampling Rate=12Hz, Parameters=1.7B, Variant=VD2026.0487.17655.272.77
Qwen3TTS-12Hz-1.7B-VDFrame rate=12Hz, Parameters=1.7B2026.0185.281.165.1—
Ming-omni-tts-0.5BParameters=0.5B2026.0484.972.253.970.33
CapTalk-1.5BParameters=1.5B2026.0484.175.461.773.73
Qwen3TTS-25Hz-1.7B-CustomVoiceFrame rate=25Hz, Parameters=1.7B2026.0183.17563—
Qwen3TTS-12Hz-1.7B-CustomVoiceFrame rate=12Hz, Parameters=1.7B2026.018377.861.2—
VoiceSculptor-VD & VCVoice Design (VD)=true, Voice Conversion (VC)=true, RAG=true2026.0177.265.159.667.3
MiMo-Audio-7B-Instruct2025.1275.7474.361.5470.52
Mimo-Audio-7B-InstructParameters=7B2026.0175.774.361.5—
VoiceSculptor2026.0175.764.761.5—
VoiceSculptor-VDVoice Design (VD)=true, RAG=true2026.0175.764.761.567.6
VoiceSculptor2026.0473.7765.447.662.26
MiMo-Audio-7B-Instruct2026.0170.166.157.164.5
GPT-4o-mini-tts2025.1254.952.34651.07
GPT-4o-mini-tts2026.0154.952.346—
GPT-4o-Mini-TTSCommercial=true2026.0154.952.34651.1
VoxInstruct2026.0147.552.342.6—
VoxInstruct2026.0147.552.342.647.5
ElevenLabsCommercial=true2026.0142.850.959.150.9
Fish Speech S2 Pro2026.0429.6150.842.641