List your company

Text-to-Speech on EmergentTTS (eval)

6.35Overall WERGemini-2.5-Flash-Preview-TTS
5.703210.069114.43518.8009Mar 9, 2026Mar 23, 2026Apr 7, 2026Apr 22, 2026May 6, 2026May 21, 2026Jun 5, 2026

Evaluation results

MethodLinks
Gemini-2.5-Flash-Preview-TTSStrong Prompting=true2026.036.3579.10.7197.3211.865.5618.3891.250.474.820.567.14—
Gemini-2.5-Flash-Preview-TTSStrong Prompting=false2026.036.59780.69512.9963.0318.2589.10.3674.820.7368.03—
minimax/speech-02-hdStrong Prompting=false2026.036.7940.960.5741.614.5831.9617.6933.570.2752.140.8445.53—
gpt-4o-mini-ttsStrong Prompting=true2026.037.1161.980.7167.3212.0763.0321.3363.390.6654.280.8461.96—
gpt-4o-mini-audio-previewStrong Prompting=false2026.037.1855.150.9562.914.4864.8219.0452.140.5545.710.8850.17—
Baseline gpt-4o-mini-ttsStrong Prompting=false2026.037.23500.72—13.45—20.55—0.42—1.04——
Fish Audio S1Strong Prompting=false2026.037.636.880.7524.8215.7753.7520.0237.680.7243.550.7424.64—
gpt-4o-audio-previewStrong Prompting=true, variant=row 82026.037.6464.90.9367.1413.7571.620.5677.321.7249.641.2658.92—
11Labs eleven multilingual v2Strong Prompting=false2026.037.6436.960.6335.3514.4436.621.5152.140.4928.211.1532.5—
gpt-4o-audio-previewStrong Prompting=true, variant=row 52026.037.7577.361.8296.9613.37021.1589.461.3862.51.1668.39—
Gemini-2.5-Pro-Preview-TTSStrong Prompting=true2026.037.91730.8792.1416.2263.4420.8784.280.7265.710.8760—
Fish Audio S2Strong Prompting=true2026.038.1581.880.5286.6114.7463.3924.5891.610.3884.410.5183.39—
ResembleAI ChatterboxStrong Prompting=false2026.038.227.391.1828.0317.5924.6420.6417.320.6551.070.9615.89—
gpt-4o-audio-previewStrong Prompting=false2026.038.2760.531.0356.7814.7268.7523.1671.61.1948.751.2556.78—
HumeAIStrong Prompting=true2026.038.6249.120.8371.7821.0541.2519.8442.140.3842.140.9348.57—
gpt-4o-mini-audio-previewStrong Prompting=true, variant=row 72026.038.8666.279.3474.112.773.3920.9268.030.7455.530.7260.35—
KyutAI-TTSStrong Prompting=false2026.039.124.280.8331.7816.4713.3926.4124.280.6135.171.1916.78—
MiniMax/speech-02-hd⋆Voice=EN-narr2026.0610.0236.6—40.9—34.3—34.3—47.3—43.916.3
DeepGram Aura-2Strong Prompting=false2026.0310.2425.213.4517.521.4115.8923.7320.891.2443.031.3628.75—
Gemini-2.5-Flash-TTS⋆Voice=Zephyr2026.0610.3970.7—95.9—58.5—91.3—63—57.955.7
dots.tts (SOAR)Voice=basic_ref_en2026.0610.4547.6—63.9—39.4—52.7—47—65.716.4
Kokoro-82MStrong Prompting=false2026.0310.4925.460.7118.0322.1713.2128.375.890.5643.390.6546.78—
BASELINE: gpt-4o-mini-ttsVoice=Alloy2026.0610.6150———————————
gpt-4o-mini-tts⋆Voice=Alloy2026.0610.7656.3—59.2—57.3—58.8—52.7—57.152.4
dots.tts (Pretrain)Voice=basic_ref_en2026.0610.8649.2—72.7—39.5—54.7—48.4—58.418
11Labs Multilingual v2⋆Voice=Brian2026.0611.1933.9—30.4—35.5—45.5—39.5—35.514.5
dots.tts (MF4)Voice=basic_ref_en2026.0611.7547.9—59.8—36.3—55.2—50.5—64.816.7
Gemini-2.5-Pro-TTS⋆Voice=Zephyr2026.0611.7969.3—86.9—58.2—82.3—61.3—61.864.8
Higgs Audio V2Strong Prompting=false2026.0311.8244.640.9769.2822.2621.4231.3445.533.2345.351.2941.6—
VoxCPM2Voice=basic_ref_en2026.0611.8441.1—42.3—33.3—44.1—53.4—52.318.6
gpt-4o-audio-preview⋆Voice=Ballad2026.0611.8765.2—88.8—60.2—82.1—57—59.540.4
F5TTSStrong Prompting=false2026.0311.9319.430.729.6423.513.2131.6619.821.6219.462.1425—
HumeAI⋆2026.0612.8542.7—61.6—34.6—36.9—43.2—44.634.3
Orpheus TTSStrong Prompting=false2026.0313.6332.561.8139.0622.3114.6440.9448.571.4831.071.6329.46—
F5-TTSVoice=basic_ref_en2026.0616.4715.3—26.8—1.8—21.6—14.8—23.81.4
Qwen3-TTSVoice=basic_ref_en2026.0617.3242.8—39.8—25.4—50.7—48.9—60.430
Qwen 2.5 OmniStrong Prompting=true2026.0318.3432.942.4146.626.7714.4658.4421.250.8748.923.4733.75—
Qwen3-TTSVoice=Ryan2026.0619.6542.3—60.5—17.1—62.7—56.4—439.8
Qwen 2.5 OmniStrong Prompting=false2026.0320.0230.251.2241.0726.9812.557.4820.8912.7749.11.6627.67—
MiniCPM-oStrong Prompting=false2026.0322.5219.7512.3622.8533.465.8958.4821.65.2122.143.0826.25—