ListenSpeedScoresCapabilitiesπŸ—³ Vote β†—

Speed

TTFA = time to first audio (lower is better). RTFx = realtime speed (Γ— realtime; higher is better). Cold = first run after load; warm = subsequent runs. Pick a rig below β€” each shows its default-voice and cloning runs. Tables default to warm RTFx, fastest first; click any column header to re-sort. Audio is on the Listen page.
Voice:
Default voiceCloning
Rig:
windows-5090 linux-3090 mac-m4
Rig: windows-5090 β€” AMD Ryzen 9 9950X3D 16-Core Processor (16C) Β· NVIDIA GeForce RTX 5090 32GB Β· 126 GB RAM Β· Windows 11

Default voice Β· 44 models Β· sorted fastest first Β· full report β†—

ModelDeviceTTFA coldTTFA warmRTFx coldRTFx warmPeak RAMPeak VRAMSizeReleased
Kokorocuda895ms67ms8.32Γ—103.68Γ—2.43 GB925 MB82MDec 2024
MeloTTScuda1.61s117ms4.60Γ—60.41Γ—2.89 GB1.16 GB~52MFeb 2024
Pipercpu160ms107ms38.94Γ—58.83Γ—470 MBβ€”~25MBJan 2023
StyleTTS 2cpu1.74s251ms4.93Γ—33.76Γ—2.61 GBβ€”~148MJun 2023
StyleTTS 2cuda1.76s265ms4.80Γ—32.15Γ—2.60 GB1.49 GB~148MJun 2023
OpenVoice v2cuda1.85s361ms3.65Γ—16.93Γ—2.65 GB1.35 GB~100MApr 2024
Kokorocpu609ms532ms12.13Γ—14.38Γ—1.82 GBβ€”82MDec 2024
Supertonic 3cpu744ms741ms9.86Γ—9.92Γ—570 MBβ€”99MMay 2026
MeloTTScpu1.88s794ms3.68Γ—9.40Γ—2.48 GBβ€”~52MFeb 2024
OmniVoicecuda1.12s757ms6.44Γ—9.30Γ—2.07 GB2.16 GB~1BMar 2026
Scylla's Bandcpu1.62s793ms3.51Γ—7.46Γ—1.04 GBβ€”~103MJul 2026
LongCat-AudioDiT 1Bcuda1.76s1.19s5.10Γ—6.69Γ—2.22 GB5.71 GB1.42BMar 2026
KittenTTS Nano 0.1cpu1.22s1.20s6.40Γ—6.39Γ—338 MBβ€”<100MAug 2025
F5-TTS v1cuda1.31s845ms3.47Γ—5.32Γ—2.67 GB802 MB330MOct 2024
Coqui XTTS-v2cuda2.05s1.87s3.63Γ—4.75Γ—2.10 GB2.14 GB750MOct 2023
Chatterbox Turbocuda2.39s1.62s2.80Γ—4.28Γ—2.44 GB3.01 GB744MDec 2025
LongCat-AudioDiT 3.5Bcuda2.27s1.80s3.41Γ—4.24Γ—2.22 GB14.96 GB3.83BMar 2026
OpenVoice v2cpu2.83s1.48s2.10Γ—4.10Γ—2.78 GBβ€”~100MApr 2024
Pocket-TTScpu147ms123ms3.99Γ—4.06Γ—1.95 GBβ€”100MJan 2026
Soprano 1.1 80Mcuda1.74s1.77s3.77Γ—3.76Γ—2.12 GB326 MB80MJan 2026
Qwen3-TTS 1.7B (CUDA-graph)cuda6.51s1.60s0.90Γ—3.76Γ—2.48 GB4.89 GB1.7BJan 2026
Echo-TTScuda2.83s2.15s2.63Γ—3.44Γ—1.94 GB9.38 GB2.8BDec 2025
Soprano 1.1 80Mcpu1.97s2.00s3.40Γ—3.40Γ—1.34 GBβ€”80MJan 2026
NeuTTS Nanocuda678ms258ms2.19Γ—2.76Γ—3.24 GB3.26 GB229MDec 2025
DramaBoxcuda5.14s3.78s1.93Γ—2.58Γ—2.36 GB17.39 GB3.3BApr 2026
VibeVoice Realtime 0.5Bcuda3.80s3.77s2.24Γ—2.39Γ—1.88 GB2.62 GB0.5BDec 2025
Chatterboxcuda3.35s2.61s1.66Γ—2.24Γ—2.80 GB3.24 GB1.2BApr 2025
NeuTTS Nanocpu698ms303ms1.73Γ—2.00Γ—5.03 GBβ€”229MDec 2025
Magpie-TTScuda5.48s4.48s1.53Γ—1.93Γ—3.54 GB5.60 GB357MDec 2025
NeuTTS Aircuda1.15s417ms1.34Γ—1.62Γ—3.60 GB3.26 GB748MSep 2025
MOSS-TTS-Nanocuda5.83s4.92s1.36Γ—1.61Γ—2.42 GB777 MB100MApr 2026
VibeVoice 1.5Bcuda4.99s5.32s1.44Γ—1.61Γ—2.04 GB5.26 GB1.5BAug 2025
VibeVoice 7Bcuda5.67s6.17s1.39Γ—1.55Γ—2.05 GB17.63 GB7BSep 2025
MOSS-TTS v1.0cuda5.23s4.74s1.34Γ—1.48Γ—2.08 GB22.83 GB8BFeb 2026
VoxCPM2 2Bcuda5.36s5.19s1.35Γ—1.35Γ—6.18 GB5.65 GB2BApr 2026
IndexTTS-2cpu6.48s5.42s1.09Γ—1.31Γ—5.56 GBβ€”1.5BJun 2025
NeuTTS Aircpu1.20s471ms1.16Γ—1.29Γ—5.37 GBβ€”748MSep 2025
LFM2.5-Audio 1.5Bcpu391ms84ms1.02Γ—1.26Γ—2.25 GBβ€”1.5BDec 2025
MOSS-TTS-Nanocpu6.38s5.64s1.08Γ—1.21Γ—3.14 GBβ€”100MApr 2026
LFM2.5-Audio 1.5Bcuda410ms91ms0.99Γ—1.18Γ—2.25 GB3.18 GB1.5BDec 2025
IndexTTS-2cuda7.20s6.03s0.93Γ—1.11Γ—5.88 GB7.60 GB1.5BJun 2025
Parler-TTS Mini v1cuda8.29s8.14s0.96Γ—1.05Γ—3.19 GB2.63 GB878MJun 2024
MOSS-TTS v1.5cuda7.66s6.86s0.88Γ—0.99Γ—2.38 GB22.83 GB8BMay 2026
Fish Speech 1.5cuda8.53s7.84s0.81Γ—0.94Γ—3.83 GB1.80 GB~500MNov 2024
Coqui XTTS-v2cpu9.92s9.73s0.87Γ—0.88Γ—3.23 GBβ€”750MOct 2023
Chatterbox Turbocpu10.65s9.92s0.70Γ—0.73Γ—4.16 GBβ€”744MDec 2025
Zonos v0.1cuda10.88s10.38s0.66Γ—0.71Γ—6.51 GB4.48 GB1.6BFeb 2025
Qwen3-TTS 1.7B Basecuda10.77s8.95s0.55Γ—0.70Γ—2.42 GB4.64 GB1.7BJan 2026
VibeVoice Realtime 0.5Bcpu14.49s13.35s0.63Γ—0.66Γ—5.89 GBβ€”0.5BDec 2025
ZipVoice 123M (4/5 ok)cuda68.83s86.51s0.35Γ—0.60Γ—25.87 GB53.16 GB123MJun 2025
Maya1cuda16.57s14.80s0.53Γ—0.59Γ—2.42 GB6.72 GB3BOct 2025
Dia 1.6B-0626cuda25.42s22.82s0.46Γ—0.55Γ—4.42 GB6.32 GB1.6BJun 2025
Sesame CSM-1Bcuda12.01s12.45s0.52Γ—0.54Γ—2.38 GB3.51 GB1BMar 2025
ZipVoice 123M (3/5 ok)cpu22.96s13.44s0.27Γ—0.45Γ—35.45 GBβ€”123MJun 2025
VoxCPM2 2Bcpu15.35s14.85s0.46Γ—0.45Γ—10.14 GBβ€”2BApr 2026
Chatterboxcpu14.47s14.10s0.40Γ—0.43Γ—4.24 GBβ€”1.2BApr 2025
OmniVoicecpu16.45s15.98s0.38Γ—0.39Γ—3.05 GBβ€”~1BMar 2026
OuteTTS 1.0 1Bcuda25.01s24.27s0.32Γ—0.33Γ—2.59 GB3.67 GB1BApr 2025
Miso TTS 8Bcuda36.25s32.11s0.30Γ—0.31Γ—2.01 GB16.53 GB8.2BMay 2026
Magpie-TTScpu37.17s33.72s0.29Γ—0.30Γ—6.10 GBβ€”357MDec 2025
Mars5-TTScpu31.19s30.69s0.22Γ—0.24Γ—4.03 GBβ€”1.2BJun 2024
Mars5-TTScuda31.20s31.06s0.23Γ—0.23Γ—2.25 GB6.81 GB1.2BJun 2024
VibeVoice 1.5Bcpu39.59s45.31s0.19Γ—0.20Γ—11.62 GBβ€”1.5BAug 2025
Qwen3-TTS 1.7B Basecpu34.81s30.07s0.18Γ—0.19Γ—10.40 GBβ€”1.7BJan 2026
Fish Speech 1.5cpu45.73s45.34s0.17Γ—0.17Γ—4.46 GBβ€”~500MNov 2024
Parler-TTS Mini v1cpu63.39s62.77s0.14Γ—0.14Γ—4.31 GBβ€”878MJun 2024
Zonos v0.1cpu62.12s60.57s0.12Γ—0.12Γ—7.39 GBβ€”1.6BFeb 2025
Sesame CSM-1Bcpu50.90s57.54s0.11Γ—0.12Γ—5.77 GBβ€”1BMar 2025
F5-TTS v1cpu58.77s60.21s0.07Γ—0.07Γ—2.59 GBβ€”330MOct 2024
Maya1 (2/4 ok)cpu66.31s73.66s0.07Γ—0.07Γ—7.33 GBβ€”3BOct 2025
LuxTTScpuLuxTTS install failed (piper-phonemize has no Windows wheels)