whatmodel.sh · find the best text-to-speech models you can run

Best text-to-speech models for a 24GB Mac

A leaderboard of the best text-to-speech models for a Mac with 24GB of memory. The best one that runs on it right now is Voxtral TTS (4B), followed by LongCat-AudioDiT-3.5B and LongCat-AudioDiT-1B. Models are ranked by one score that combines 101 published benchmarks. Models that run on it show the download that fits and the command to run it.

122 models · scores combine 101 benchmarks · updated how it works · find a leaderboard · benchmark your machine
task[all tasks][voice cloning]
Models for 24GB RAM · Apple Silicon → ~16GB fast · reset
+ more
chip[M2][M3][M4][M4 Pro][M5][M5 Pro][M6 (24/32GB)]
set[all sets][Vapi Humanness · Bradley–Terry rating, 2026-09-25 snapshot · 148][VITS 2021 LJ Speech human MOS · 5][Grad-TTS 2021 LJ Speech human MOS · 4]

Filter the model list while keeping overall scores. Models without a shared score scale are not yet calibrated; select a set to see its own scores.

Detect your exact chip or graphics card:

curl -G whatmodel.sh/tts -d max=0 --data-urlencode "mac=$(sysctl -n hw.memsize machdep.cpu.brand_string)"Mac

curl -G whatmodel.sh/tts -d max=0 --data-urlencode "ram=$(awk '/MemT/{print $2}' /proc/meminfo)" --data-urlencode "nv=$(nvidia-smi --query-gpu=name,memory.total --format=csv,noheader 2>/dev/null)"Linux

curl.exe -G whatmodel.sh/tts -d max=0 --data-urlencode "ram=$((gcim Win32_ComputerSystem).TotalPhysicalMemory)" --data-urlencode "nv=$(nvidia-smi --query-gpu=name,memory.total --format=csv,noheader 2>$null)"Windows

$ terminal

detecting your OS…

Run curl "whatmodel.sh/tts?ram=24&gpu=apple"to get this list in your terminal (add &format=json for agents).

ram[8][16][24][32][48][64][96][128][192][256]GB
gpu[apple silicon][graphics card][none]
price[local][$1][$2][$5][$10][$20][$50][any]max per M chars

detecting your OS…

Score vs API price

#modelscore↓where↓speed↓RAM↓get itsources
#modelscore↓where↓speed↓RAM↓get itsources
4Voxtral TTS (4B) · bf16 Mistral71±4†local~10GBhow to run › Voxtral TTS
5OpenAudio S1 Fish Audio71±8*†api $15.00/M charsdocs.fish.audio ↗Fish Audio S2 Technical Report
7Qwen-Audio-3.0-TTS-Plus Alibaba69±2†api $20.00/M charswww.alibabacloud.com ↗Qwen-Audio-3.0-TTS technical report
8Gemini 3.1 Flash TTS Preview Google69±2api $50.00/M charsfal.ai ↗ZONOS2 Technical Report (ZTTS1-Eval results)Building and Evaluating Fixed-Voice Thai TTS from Synthetic Speech (Wayu Research / Paxa Labs / Typhoon; arXiv:2609.03502v1)RW-Voice-EQ Bench (Hume AI)nsanku TTS Benchmark (GhanaNLP community Space)ZTTS1-Eval results snapshot (Zyphra)Arabic TTS Arena (Navid AI) · leaderboard snapshot 2026-09-24+1
11Grok TTS xAI68±3api $15.00/M charsdocs.x.ai ↗The Humanness Index by Vapi · September 2026 public standingsThe Humanness Index by Vapi · June 2026 production exportArabic TTS Arena (Navid AI) · leaderboard snapshot 2026-09-24
13Simba 3.2 Speechify67±3*api $6.00/M charsspeechify.ai ↗The Humanness Index by Vapi · September 2026 public standings
15MiniMax Speech 2.8 Turbo MiniMax66±3*api $60.00/M charsplatform.minimax.io ↗The Humanness Index by Vapi · September 2026 public standings
16LongCat-AudioDiT-3.5B · fp32 weights (official LongCat-AudioDiT repo, transformers>=5.3) Meituan66±2local~15GBhow to run › Qwen-Audio-3.0-TTS technical reportmeituan-longcat/LongCat-AudioDiT-3.5B model card (Seed benchmark table)
17LongCat-AudioDiT-1B · fp32 weights (official LongCat-AudioDiT repo, transformers>=5.3) Meituan66±4†local~5.7GBhow to run › meituan-longcat/LongCat-AudioDiT-3.5B model card (Seed benchmark table)
18OmniVoice · fp32 k2-fsa (Xiaomi)66±2local~3.3GBhow to run › OmniVoice: Towards Omnilingual Zero-Shot Text-to-Speech with Diffusion Language Models (arXiv:2604.00688v3)Building and Evaluating Fixed-Voice Thai TTS from Synthetic Speech (Wayu Research / Paxa Labs / Typhoon; arXiv:2609.03502v1)nineninesix/gepard-1.0 model card (Seed-TTS-eval benchmark table)Higgs Audio v3 comparison tables in SGLang-Omni cookbook (Boson AI contribution)nsanku TTS Benchmark (GhanaNLP community Space)Arabic TTS Arena (Navid AI) · leaderboard snapshot 2026-09-24
19MiniMax Speech 2.8 HD MiniMax66±2api $100.00/M charsplatform.minimax.io ↗Qwen-Audio-3.0-TTS technical reportCN-NewsTTS Bench v0.1Preferences of a Voice-First Nation: pairwise human evaluation of TTS in 10 Indian languages (arXiv:2604.21481v2)
21Eleven v3 ElevenLabs65±1api $100.00/M charselevenlabs.io ↗Qwen-Audio-3.0-TTS technical reportZONOS2 Technical Report (ZTTS1-Eval results)The Humanness Index by Vapi · September 2026 public standingsVoxtral TTSThe Humanness Index by Vapi · June 2026 production exportRW-Voice-EQ Bench (Hume AI)+2
22Chirp 3: HD Google65±4*api $30.00/M charscloud.google.com ↗CN-NewsTTS Bench v0.1
23Higgs Audio V3 TTS · bf16 Boson AI65±3local~10GBhow to run › Higgs Audio v3 comparison tables in SGLang-Omni cookbook (Boson AI contribution)RW-Voice-EQ Bench (Hume AI)RVCBench: Benchmarking Robustness of Voice Cloning Across Modern Audio Generation Models (arXiv:2602.00443v2)Arabic TTS Arena (Navid AI) · leaderboard snapshot 2026-09-24
25Qwen3-TTS 12Hz 1.7B Base · bf16 (qwen-tts) Alibaba (Qwen)65±1local~4.5GBhow to run › UltraEval-Audio (OpenBMB) · TTS replication resultsRaon-OpenTTS: Open Models and Data for Robust Text-to-Speech (arXiv:2605.20830v2)Qwen-Audio-3.0-TTS technical reportZONOS2 Technical Report (ZTTS1-Eval results)Higgs Audio v3 comparison tables in SGLang-Omni cookbook (Boson AI contribution)Qwen/Qwen3-TTS-12Hz-1.7B-Base model card+3
27VoxCPM2 · bf16 (voxcpm) OpenBMB64±1local~5GBhow to run › UltraEval-Audio (OpenBMB) · TTS replication resultsQwen-Audio-3.0-TTS technical reportZONOS2 Technical Report (ZTTS1-Eval results)nineninesix/gepard-1.0 model card (Seed-TTS-eval benchmark table)ZTTS1-Eval results snapshot (Zyphra)Arabic TTS Arena (Navid AI) · leaderboard snapshot 2026-09-24
28Fun-CosyVoice3-0.5B-2512 · fp32 (CosyVoice repo) Alibaba (FunAudioLLM)64±1local~5.4GBhow to run › UltraEval-Audio (OpenBMB) · TTS replication resultsRaon-OpenTTS: Open Models and Data for Robust Text-to-Speech (arXiv:2605.20830v2)Qwen-Audio-3.0-TTS technical report
29Wayu-Paxa-TTS-Edge · fp32 (wayu-tts package) Wayu Research / Paxa Labs64±4†local~0.3GBhow to run › Building and Evaluating Fixed-Voice Thai TTS from Synthetic Speech (Wayu Research / Paxa Labs / Typhoon; arXiv:2609.03502v1)
30Eleven Turbo v2.5 ElevenLabs64±4*api $50.00/M charselevenlabs.io ↗The Humanness Index by Vapi · June 2026 production export
31Fish Audio S2.1 Pro Fish Audio63±3*api $15.00/M charsdocs.fish.audio ↗The Humanness Index by Vapi · September 2026 public standings
32IndexTTS-2 · fp32 (index-tts repo) IndexTeam (bilibili)63±1local~8.9GBhow to run › UltraEval-Audio (OpenBMB) · TTS replication resultsVoxCPM: Tokenizer-Free TTS for Context-Aware Speech Generation and True-to-Life Voice Cloning (arXiv:2509.24650v1)OmniVoice: Towards Omnilingual Zero-Shot Text-to-Speech with Diffusion Language Models (arXiv:2604.00688v3)Raon-OpenTTS: Open Models and Data for Robust Text-to-Speech (arXiv:2605.20830v2)Higgs Audio v3 comparison tables in SGLang-Omni cookbook (Boson AI contribution)An Evaluation Framework for TTS Voice Reconstruction (SAP dysarthric speakers; arXiv:2606.21343v1)+2
36MiniMax Speech-02-HD MiniMax63±3api $100.00/M charsplatform.minimax.io ↗The Humanness Index by Vapi · September 2026 public standingsEmergentTTS-Eval six-category leaderboard
37Fish Audio S2 Pro · bf16 (fish-speech official repo CLI) Fish Audio63±1local~11GBhow to run › UltraEval-Audio (OpenBMB) · TTS replication resultsZONOS2 Technical Report (ZTTS1-Eval results)RW-Voice-EQ Bench (Hume AI)nineninesix/gepard-1.0 model card (Seed-TTS-eval benchmark table)Higgs Audio v3 comparison tables in SGLang-Omni cookbook (Boson AI contribution)ZTTS1-Eval results snapshot (Zyphra)+3
38Eleven Flash v2.5 ElevenLabs63±2api $50.00/M charselevenlabs.io ↗The Humanness Index by Vapi · September 2026 public standingsVoxtral TTSThe Humanness Index by Vapi · June 2026 production exportRime Alpha TTS Benchmark v1.0.0 · SupportBench and ContentBench paired human preference
39IndexTTS (v1) · fp32 on CPU (index-tts repo CLI `indextts`) IndexTeam (bilibili)62±3local~1.2GBhow to run › DiSTAR: Diffusion over a Scalable Token Autoregressive Representation for Speech Generation (arXiv:2510.12210v2)
40F5-TTS v1 Base · fp32 SWivid (SJTU X-LANCE)62±3local~1.4GBhow to run › DiSTAR: Diffusion over a Scalable Token Autoregressive Representation for Speech Generation (arXiv:2510.12210v2)RVCBench: Benchmarking Robustness of Voice Cloning Across Modern Audio Generation Models (arXiv:2602.00443v2)
41Inworld TTS-1.5 Max Inworld62±3*api $10.00/M charsfal.ai ↗The Humanness Index by Vapi · September 2026 public standingsThe Humanness Index by Vapi · June 2026 production export
42ZipVoice · fp32 (ZipVoice repo) k2-fsa (Xiaomi)62±3local~0.6GBhow to run › OmniVoice: Towards Omnilingual Zero-Shot Text-to-Speech with Diffusion Language Models (arXiv:2604.00688v3)RVCBench: Benchmarking Robustness of Voice Cloning Across Modern Audio Generation Models (arXiv:2602.00443v2)
44Qwen3-TTS 12Hz 0.6B Base · bf16 (qwen-tts) Alibaba (Qwen)62±2local~2.5GBhow to run › UltraEval-Audio (OpenBMB) · TTS replication resultsQwen/Qwen3-TTS-12Hz-1.7B-Base model cardSGLang-Omni serving cookbooks (SGLang-Omni team measurements)
45Eleven Flash v2 ElevenLabs62±3*api $50.00/M charselevenlabs.io ↗The Humanness Index by Vapi · September 2026 public standingsThe Humanness Index by Vapi · June 2026 production export
47Eleven Turbo v2 ElevenLabs61±3*api $50.00/M charselevenlabs.io ↗The Humanness Index by Vapi · September 2026 public standingsThe Humanness Index by Vapi · June 2026 production export
48Inworld Realtime TTS-2 Inworld61±2api $25.00/M charsreplicate.com ↗ZONOS2 Technical Report (ZTTS1-Eval results)The Humanness Index by Vapi · September 2026 public standingsThe Humanness Index by Vapi · June 2026 production exportRW-Voice-EQ Bench (Hume AI)
49CosyVoice2-0.5B · fp32 (CosyVoice repo) Alibaba (FunAudioLLM)61±1local~4.1GBhow to run › UltraEval-Audio (OpenBMB) · TTS replication resultsRaon-OpenTTS: Open Models and Data for Robust Text-to-Speech (arXiv:2605.20830v2)VoxCPM: Tokenizer-Free TTS for Context-Aware Speech Generation and True-to-Life Voice Cloning (arXiv:2509.24650v1)DMOSpeech 2: Reinforcement Learning for Duration Prediction in Metric-Optimized Speech Synthesis (arXiv:2507.14988v1)DiSTAR: Diffusion over a Scalable Token Autoregressive Representation for Speech Generation (arXiv:2510.12210v2)RVCBench: Benchmarking Robustness of Voice Cloning Across Modern Audio Generation Models (arXiv:2602.00443v2)+1
50E2 TTS Base (F5-TTS reproduction) · fp32 SWivid (SJTU X-LANCE)60±2local~1.3GBhow to run › DiSTAR: Diffusion over a Scalable Token Autoregressive Representation for Speech Generation (arXiv:2510.12210v2)F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching (arXiv:2410.06885v1)TTSDS2 listening test results (ttsds/listening_test)An Evaluation Framework for TTS Voice Reconstruction (SAP dysarthric speakers; arXiv:2606.21343v1)TTSDS2 multilingual benchmark results (ttsds/leaderboard_data)
51MiniMax Speech-02-Turbo MiniMax60±3*api $60.00/M charsplatform.minimax.io ↗The Humanness Index by Vapi · September 2026 public standings
52TTS-1 OpenAI59±4api $15.00/M charsdevelopers.openai.com ↗RW-Voice-EQ Bench (Hume AI)
55CosyVoice v3 Plus Alibaba Cloud58±4*api $26.00/M charswww.alibabacloud.com ↗CN-NewsTTS Bench v0.1
56Octave TTS (Octave 1) Hume AI58±4api $50.00/M charswww.hume.ai ↗EmergentTTS-Eval six-category leaderboardInstructTTSEval: instruction-following TTS benchmark (arXiv:2506.16381v1)EmergentTTS-Eval v1 paper (arXiv:2505.23009v1) · Table 1 automatic MOS
57Sonic 3 Cartesia58±2api $65.00/M charswww.together.ai ↗The Humanness Index by Vapi · September 2026 public standingsThe Humanness Index by Vapi · June 2026 production exportRime Alpha TTS Benchmark v1.0.0 · SupportBench and ContentBench paired human preferencePreferences of a Voice-First Nation: pairwise human evaluation of TTS in 10 Indian languages (arXiv:2604.21481v2)
60F5-TTS Base (v0) · fp32 SWivid (SJTU X-LANCE)57±2local~1.4GBhow to run › F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching (arXiv:2410.06885v1)TTSDS2 listening test results (ttsds/listening_test)TTSDS2 multilingual benchmark results (ttsds/leaderboard_data)
61TTS-1 HD OpenAI57±7*api $30.00/M charsdevelopers.openai.com ↗RW-Voice-EQ Bench (Hume AI)
62Deepgram Aura 2 Deepgram57±3api $30.00/M charsdeepgram.com ↗Rime Alpha TTS Benchmark v1.0.0 · SupportBench and ContentBench paired human preferenceEmergentTTS-Eval six-category leaderboardRW-Voice-EQ Bench (Hume AI)EmergentTTS-Eval v1 paper (arXiv:2505.23009v1) · Table 1 automatic MOS
63ZONOS2 8B · mlx-bf16 (mlx-audio) Zyphra57±2†local~16GBhow to run › ZONOS2 Technical Report (ZTTS1-Eval results)ZTTS1-Eval results snapshot (Zyphra)
64Supertonic 3 · onnx-fp32 (supertonic Python SDK 1.3.x) Supertone55±10*local~0.4GBhow to run › Arabic TTS Arena (Navid AI) · leaderboard snapshot 2026-09-24
66Higgs Audio V2 · mlx-8bit (mlx-audio) Boson AI55±3local~7GBhow to run › Higgs Audio v3 comparison tables in SGLang-Omni cookbook (Boson AI contribution)EmergentTTS-Eval six-category leaderboardRVCBench: Benchmarking Robustness of Voice Cloning Across Modern Audio Generation Models (arXiv:2602.00443v2)
68CosyVoice-300M · fp32 (CosyVoice repo) Alibaba (FunAudioLLM)54±3local~2.3GBhow to run › F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching (arXiv:2410.06885v1)VERSA toolkit paper: TTS demonstration (arXiv:2412.17667v2)Amphion MaskGCT README · zero-shot TTS results table
69Chatterbox Multilingual V3 · fp32 (chatterbox) Resemble AI54±10*local~3.2GBhow to run › Arabic TTS Arena (Navid AI) · leaderboard snapshot 2026-09-24
70VibeVoice 1.5B · bf16 (transformers >=5.17.0) Microsoft53±6local~5.4GBhow to run › RVCBench: Benchmarking Robustness of Voice Cloning Across Modern Audio Generation Models (arXiv:2602.00443v2)Microsoft VibeVoice own subjective evaluation figure
71Lightning v3.1 Smallest.ai53±3*api $17.50/M charssmallest.ai ↗The Humanness Index by Vapi · September 2026 public standingsRW-Voice-EQ Bench (Hume AI)
73Kokoro 82M v1.0 · bf16 hexgrad52±3local~0.7GBhow to run › EmergentTTS-Eval six-category leaderboardParadee: Distilling Kokoro-82M into an 8M-Parameter Single-Voice TTS Model (arXiv:2610.06817v1), Table 3 small-model comparisoncarun/tts-bench: intelligibility benchmark of four open TTS engines (published run, 2026-09-10)RW-Voice-EQ Bench (Hume AI)
74LEMAS-TTS (w/ prosody, multilingual_prosody) · official checkpoint (LEMAS-TTS repo, F5-TTS-based) LEMAS Project52±6*†local~1.5GBhow to run › LEMAS multilingual audio suite report
76Spark-TTS 0.5B · fp32 (Spark-TTS repo CLI) SparkAudio52±3local~3.9GBhow to run › DMOSpeech 2: Reinforcement Learning for Duration Prediction in Metric-Optimized Speech Synthesis (arXiv:2507.14988v1)RVCBench: Benchmarking Robustness of Voice Cloning Across Modern Audio Generation Models (arXiv:2602.00443v2)
78Gradium TTS Gradium51±3*api $38.00/M charsdocs.gradium.ai ↗The Humanness Index by Vapi · September 2026 public standingsThe Humanness Index by Vapi · June 2026 production export
79OpenVoice V1 · fp32 (myshell-ai/OpenVoice) MyShell51±14*local~0.3GBhow to run › TTSDS v1 published results
80Eleven Multilingual v2 ElevenLabs51±5api $100.00/M charselevenlabs.io ↗EmergentTTS-Eval six-category leaderboardEmergentTTS-Eval v1 paper (arXiv:2505.23009v1) · Table 1 automatic MOS
84LEMAS-TTS (w/o prosody, multilingual_grl) · official checkpoint (LEMAS-TTS repo, F5-TTS-based) LEMAS Project50±6*†local~1.4GBhow to run › LEMAS multilingual audio suite report
85MMS TTS Amharic · fp32 (transformers VitsModel) Meta50±16*local~0.2GBhow to run › Addis AI Amharic TTS benchmark
86Chatterbox · fp32 (chatterbox-tts 0.1.7) Resemble AI50±5local~3.2GBhow to run › EmergentTTS-Eval six-category leaderboardCodecMOS-Accent: listening-test MOS of zero-shot TTS across English accents (arXiv:2603.14328v1)
87Parler-TTS Mini v0.1 · fp32 Hugging Face (Parler-TTS)49±14*local~2.6GBhow to run › TTSDS v1 published results
89SILMA TTS v1 · fp32 checkpoint (silma-tts 1.0.5) SILMA AI48±10*local~2.7GBhow to run › Arabic TTS Arena (Navid AI) · leaderboard snapshot 2026-09-24
92Orpheus TTS 3B 0.1 (finetune-prod) · gguf Q4_K_M (orpheus-cpp 0.0.3) Canopy Labs47±5local~2.4GBhow to run › EmergentTTS-Eval six-category leaderboardEmergentTTS-Eval v1 paper (arXiv:2505.23009v1) · Table 1 automatic MOS
93Kyutai TTS 1.6B en/fr · bf16 (moshi-mlx) Kyutai47±5*local~4.1GBhow to run › EmergentTTS-Eval six-category leaderboard
96Piper (en_US lessac medium) · onnx-fp32 (piper-tts 1.8.0) Open Home Foundation (Piper)47±5*local~0.1GBhow to run › Paradee: Distilling Kokoro-82M into an 8M-Parameter Single-Voice TTS Model (arXiv:2610.06817v1), Table 3 small-model comparison
97Vevo (Amphion) · fp32 (Amphion repo) Amphion (CUHK-Shenzhen)46±3local~6.8GBhow to run › TTSDS2 listening test results (ttsds/listening_test)An Evaluation Framework for TTS Voice Reconstruction (SAP dysarthric speakers; arXiv:2606.21343v1)TTSDS2 multilingual benchmark results (ttsds/leaderboard_data)CodecMOS-Accent: listening-test MOS of zero-shot TTS across English accents (arXiv:2603.14328v1)
100Amazon Polly Neural Amazon Web Services45±4*api $16.00/M charsaws.amazon.com ↗CN-NewsTTS Bench v0.1
102GPT-SoVITS v2 · fp32 (repo api_v2.py) RVC-Boss44±4local~1.1GBhow to run › TTSDS2 listening test results (ttsds/listening_test)TTSDS2 multilingual benchmark results (ttsds/leaderboard_data)
103MeloTTS English · fp32 (MeloTTS repo CLI) MyShell44±5local~0.7GBhow to run › VERSA toolkit paper: TTS demonstration (arXiv:2412.17667v2)Audio Deepfake Detection in the Age of Advanced Text-to-Speech models (arXiv:2601.20510v1)
104Parler-TTS Mini v1 · fp32 (parler-tts) Hugging Face (Parler-TTS)44±6*local~3.5GBhow to run › VERSA toolkit paper: TTS demonstration (arXiv:2412.17667v2)
106Nabra-82M v0.1 · fp32 (Kokoro KModel, Oddadmix/kokoro fork) oddadmix42±10*local~0.3GBhow to run › Arabic TTS Arena (Navid AI) · leaderboard snapshot 2026-09-24
107OpenAudio S1 Mini · bf16 (fish-speech official repo CLI) Fish Audio41±5local~3.6GBhow to run › LEMAS multilingual audio suite reportArabic TTS Arena (Navid AI) · leaderboard snapshot 2026-09-24CodecMOS-Accent: listening-test MOS of zero-shot TTS across English accents (arXiv:2603.14328v1)
108Fish Speech 1.5 · bf16 (fish-speech repo) Fish Audio41±3local~1.5GBhow to run › TTSDS2 listening test results (ttsds/listening_test)TTSDS2 multilingual benchmark results (ttsds/leaderboard_data)
109EMA Lightning · fp32 (PyTorch) EMA Lightning (canberkkkkkk)40±3*local~0GBhow to run › Antalia-2 Mini model card (cloud0day3/antalia-mini), public Freya-TR-Eval re-run tableEMA Lightning model card (canberkkkkkk/ema-lightning), Benchmarks: Freya-TR-Eval
113Magpie TTS Multilingual 357M · f16-gguf (NVIDIA NeMo-Speech.cpp) NVIDIA39±6*local~0.7GBhow to run › carun/tts-bench: intelligibility benchmark of four open TTS engines (published run, 2026-09-10)
114Zonos v0.1 · bf16 Zyphra39±4local~4.3GBhow to run › EmergentTTS-Eval six-category leaderboardbalacoon speech_gen_baselines · zero-shot TTS metrics (VCTK, DAPS-celeb)EmergentTTS-Eval v1 paper (arXiv:2505.23009v1) · Table 1 automatic MOS
115Maya1 · bf16 (transformers + snac) Maya Research38±6*local~6.7GBhow to run › Audio Deepfake Detection in the Age of Advanced Text-to-Speech models (arXiv:2601.20510v1)
116Gemini 3.8 Flash TTS Google37±3*api price unknownai.google.dev ↗Antalia-2 Mini model card (cloud0day3/antalia-mini), public Freya-TR-Eval re-run tableEMA Lightning model card (canberkkkkkk/ema-lightning), Benchmarks: Freya-TR-Eval
119Gemini 3.8 Flash-Lite TTS Google37±3*api price unknownai.google.dev ↗Antalia-2 Mini model card (cloud0day3/antalia-mini), public Freya-TR-Eval re-run tableEMA Lightning model card (canberkkkkkk/ema-lightning), Benchmarks: Freya-TR-Eval
120Eleven v4 ElevenLabs37±4*api $80.00/M charselevenlabs.io ↗EMA Lightning model card (canberkkkkkk/ema-lightning), Benchmarks: Freya-TR-Eval
121Amphion VALL-E v2 recipe (MLS) · fp32 (Amphion repo) Amphion (CUHK-Shenzhen)36±3local~2.9GBhow to run › TTSDS2 listening test results (ttsds/listening_test)VERSA toolkit paper: TTS demonstration (arXiv:2412.17667v2)TTSDS2 multilingual benchmark results (ttsds/leaderboard_data)TTSDS v1 published results
122NeuTTS Air · bf16 (neutts 1.4.1) Neuphonic36±10*local~5GBhow to run › CodecMOS-Accent: listening-test MOS of zero-shot TTS across English accents (arXiv:2603.14328v1)
123Eleven v4 Turbo ElevenLabs36±4*api $40.00/M charselevenlabs.io ↗EMA Lightning model card (canberkkkkkk/ema-lightning), Benchmarks: Freya-TR-Eval
125Sesame CSM-1B · fp32 (mlx-audio) Sesame34±5local~6.6GBhow to run › EmergentTTS-Eval six-category leaderboardbalacoon speech_gen_baselines · zero-shot TTS metrics (VCTK, DAPS-celeb)EmergentTTS-Eval v1 paper (arXiv:2505.23009v1) · Table 1 automatic MOSRW-Voice-EQ Bench (Hume AI)
126VoiceCraft 830M (giga830M) · fp32 (VoiceCraft repo) Puyuan Peng et al. (UT Austin)32±4†local~4.5GBhow to run › VoiceCraft: Zero-Shot Speech Editing and Text-to-Speech in the Wild (arXiv:2403.16973v3)
127VALL-E X (Plachtaa open implementation) · fp32 (Plachtaa/VALL-E-X repo) Plachtaa (community)31±4local~1.6GBhow to run › VERSA toolkit paper: TTS demonstration (arXiv:2412.17667v2)ClonEval · Open Voice Cloning Leaderboard (AMU)CodecMOS-Accent: listening-test MOS of zero-shot TTS across English accents (arXiv:2603.14328v1)
128OuteTTS 0.2 500M · fp32 (outetts 0.3.3) OuteAI31±6*local~1.4GBhow to run › ClonEval · Open Voice Cloning Leaderboard (AMU)
130StyleTTS 2 (LibriTTS) · fp32 (styletts2 PyPI package 0.1.6) Yinghao Aaron Li et al. (Columbia University)30±2local~0.9GBhow to run › TTSDS2 listening test results (ttsds/listening_test)ZS-TTS-Evaluation (Edresson Casanova) · zero-shot TTS metrics of XTTS, YourTTS, TorToiSe and StyleTTS 2StyleTTS-ZS: Efficient High-Quality Zero-Shot Text-to-Speech Synthesis with Distilled Time-Varying Style Diffusion (arXiv:2409.10058v1)DiTTo-TTS: Diffusion Transformers for Scalable Text-to-Speech without Domain-Specific Factors (arXiv:2406.11427v2)An Evaluation Framework for TTS Voice Reconstruction (SAP dysarthric speakers; arXiv:2606.21343v1)RVCBench: Benchmarking Robustness of Voice Cloning Across Modern Audio Generation Models (arXiv:2602.00443v2)+2
131XTTS v2 · fp32 (coqui-tts 0.27.5) Coqui30±2local~1.9GBhow to run › Antalia-2 Mini model card (cloud0day3/antalia-mini), public Freya-TR-Eval re-run tableVoiceCraft: Zero-Shot Speech Editing and Text-to-Speech in the Wild (arXiv:2403.16973v3)ZS-TTS-Evaluation (Edresson Casanova) · zero-shot TTS metrics of XTTS, YourTTS, TorToiSe and StyleTTS 2StyleTTS-ZS: Efficient High-Quality Zero-Shot Text-to-Speech Synthesis with Distilled Time-Varying Style Diffusion (arXiv:2409.10058v1)DiTTo-TTS: Diffusion Transformers for Scalable Text-to-Speech without Domain-Specific Factors (arXiv:2406.11427v2)ClonEval · Open Voice Cloning Leaderboard (AMU)+7
132Tortoise TTS v2 · fp16 (neonbjb/tortoise-tts) Tortoise29±2local~5.6GBhow to run › TTSDS2 listening test results (ttsds/listening_test)ZS-TTS-Evaluation (Edresson Casanova) · zero-shot TTS metrics of XTTS, YourTTS, TorToiSe and StyleTTS 2EmergentTTS-Eval six-category leaderboardAn Evaluation Framework for TTS Voice Reconstruction (SAP dysarthric speakers; arXiv:2606.21343v1)EmergentTTS-Eval v1 paper (arXiv:2505.23009v1) · Table 1 automatic MOSCodecMOS-Accent: listening-test MOS of zero-shot TTS across English accents (arXiv:2603.14328v1)+2
133Parler-TTS Large v1 · fp32 Hugging Face (Parler-TTS)29±3local~9.3GBhow to run › TTSDS2 listening test results (ttsds/listening_test)InstructTTSEval: instruction-following TTS benchmark (arXiv:2506.16381v1)TTSDS2 multilingual benchmark results (ttsds/leaderboard_data)TTSDS v1 published results
137Piper (tr_TR dfki medium) · onnx-fp32 (piper-tts) Open Home Foundation (Piper)26±4*local~0.1GBhow to run › Antalia-2 Mini model card (cloud0day3/antalia-mini), public Freya-TR-Eval re-run table
138OpenVoice V2 · fp32 (myshell-ai/OpenVoice) MyShell26±3local~0.8GBhow to run › TTSDS2 listening test results (ttsds/listening_test)TTSDS2 multilingual benchmark results (ttsds/leaderboard_data)RVCBench: Benchmarking Robustness of Voice Cloning Across Modern Audio Generation Models (arXiv:2602.00443v2)TTSDS v1 published results
139Bark · fp32 Suno25±3local~12GBhow to run › TTSDS2 listening test results (ttsds/listening_test)EmergentTTS-Eval six-category leaderboardEmergentTTS-Eval v1 paper (arXiv:2505.23009v1) · Table 1 automatic MOSTTSDS2 multilingual benchmark results (ttsds/leaderboard_data)TTSDS v1 published results
140SpeechT5 TTS · fp32 (transformers) Microsoft23±3local~0.7GBhow to run › TTSDS2 listening test results (ttsds/listening_test)TTSDS2 multilingual benchmark results (ttsds/leaderboard_data)
143YourTTS · fp32 (coqui-tts) Coqui / Edresson Casanova et al.18±3local~0.4GBhow to run › VoiceCraft: Zero-Shot Speech Editing and Text-to-Speech in the Wild (arXiv:2403.16973v3)ZS-TTS-Evaluation (Edresson Casanova) · zero-shot TTS metrics of XTTS, YourTTS, TorToiSe and StyleTTS 2DiTTo-TTS: Diffusion Transformers for Scalable Text-to-Speech without Domain-Specific Factors (arXiv:2406.11427v2)
144MMS TTS Turkish · fp32 (transformers VitsModel) Meta18±4*local~0.2GBhow to run › Antalia-2 Mini model card (cloud0day3/antalia-mini), public Freya-TR-Eval re-run table
147Glow-TTS Common Voice (Turkish) · fp32 · CPU Coqui TTS / Fatih Akademi11±4*local~4GBhow to run › Antalia-2 Mini model card (cloud0day3/antalia-mini), public Freya-TR-Eval re-run table
—Azure HD 2.5 Microsoftno reviewed resultsapi $22.00/M charsazure.microsoft.com ↗
—Breeze TTS 2 · mlx-bf16 (mlx-audio 0.5.7) BreezeBlueno reviewed resultslocal~7.6GBhow to run ›
—Chatterbox Turbo · fp32 (chatterbox-tts 0.1.7) Resemble AIno reviewed resultslocal~3GBhow to run ›
—Dia 1.6B (0626) · fp32 (nari-labs/dia repo) Nari Labsno reviewed resultslocal~6.8GBhow to run ›
—Eleven v3 Conversational ElevenLabsno reviewed resultsapi $40.00/M charselevenlabs.io ↗
—FastPitch (Coqui LJ Speech) · fp32 · CPU Coqui TTS / Eren Gölge @erogolno reviewed resultslocal~4GBhow to run ›
—FastSpeech 2 + HiFi-GAN (SpeechBrain LJ Speech) · fp32 · CPU SpeechBrainno reviewed resultslocal~4GBhow to run ›
—Glow-TTS (Coqui LJ Speech) · fp32 · CPU Coqui TTS / Eren Gölge @erogolno reviewed resultslocal~4GBhow to run ›
—Glow-TTS Mai (Ukrainian) · fp32 · CPU Coqui TTS / @robinhadno reviewed resultslocal~4GBhow to run ›
—Kitten TTS Mini 0.8 · fp32 (mlx-audio) KittenMLno reviewed resultslocal~0.3GBhow to run ›
—KittenTTS 2 · ternary-packed LM (kittenml 0.9.3) KittenMLno reviewed resultslocal~2.1GBhow to run ›
—Lightning v3.1 Pro Smallest.aino reviewed resultsapi $19.50/M charssmallest.ai ↗
—LightSpeech + Parallel WaveGAN · fp32 · CPU (microsoft/NeuralSpeech LightSpeech repo, LJSpeech test set) Microsoft NeuralSpeechno reviewed resultslocal~0GBhow to run ›
—MiniMax Speech 2.6 HD MiniMaxno reviewed resultsapi $100.00/M charsplatform.minimax.io ↗
—Neural HMM TTS (Coqui LJ Speech) · fp32 · CPU Coqui TTS / Shivam Metha @shivammehta25no reviewed resultslocal~4GBhow to run ›
—Octave 2 Hume AIno reviewed resultsapi $25.00/M charswww.hume.ai ↗
—OverFlow (Coqui LJ Speech) · fp32 · CPU Coqui TTS / Eren Gölge @erogolno reviewed resultslocal~4GBhow to run ›
—Pocket TTS (English) · fp32 (pocket-tts 3.3.0) Kyutaino reviewed resultslocal~0.2GBhow to run ›
—Polly Generative Amazonno reviewed resultsapi $30.00/M charsaws.amazon.com ↗
—Sonic 3.6 Cartesiano reviewed resultsapi $38.00/M charscartesia.ai ↗
—SpeedySpeech (Coqui LJ Speech) · fp32 · CPU Coqui TTS / Eren Gölge @erogolno reviewed resultslocal~4GBhow to run ›
—Tacotron 2 DDC (Coqui LJ Speech) · fp32 · CPU Coqui TTS / Eren Gölge @erogolno reviewed resultslocal~4GBhow to run ›
—VITS Common Voice (Portuguese) · fp32 · CPU Coqui TTS / @NeonGeckoComno reviewed resultslocal~4GBhow to run ›
—VITS CSS10 (French) · fp32 · CPU Coqui TTS / @NeonGeckoComno reviewed resultslocal~4GBhow to run ›
—VITS CSS10 (Spanish) · fp32 · CPU Coqui TTS / @NeonGeckoComno reviewed resultslocal~4GBhow to run ›
—VITS Thorsten (German) · fp32 · CPU Coqui TTS / @thorstenMuellerno reviewed resultslocal~4GBhow to run ›

+ 65 more don't fit your machine or budget · show them

187 of 187 catalogue models listed here · sources and licences

* new or thinly tested: ranked on too few benchmark results · † only the maker’s own numbers so far · ~RAM is estimated; full context may need more memory