| 1 | Higgs-TTS-3-4B-MLX-bf16 | bosonai/higgs-tts-3-4b | aufklarer | 80.0 | medium | |
| 2 | cosyvoice2_rknn | — | Sariel00 | 74.59 | low | |
| 3 | VibeVoice-Large-AWQ | rsxdalv/VibeVoice-Large | ncoder-ai | 54.0 | medium | RTF (i5-12600K, 7 steps) |
| 4 | w2v-bert-2.0-afrivoices-ea-6l-asr-int8-edge | leophill/w2v-bert-2.0-afrivoices-ea-6l-asr | leophill | 51.0 | medium | |
| 5 | VibeVoice-Large-AWQ | rsxdalv/VibeVoice-Large | ncoder-ai | 50.9 | medium | RTF (i7-14700KF, 5 steps) |
| 6 | whisper-small-malayalam | openai/whisper-small | sajilck | 40.0 | low | |
| 7 | Qwen3-TTS-12Hz-1.7B-Base-MLX-bf16 | Qwen/Qwen3-TTS-12Hz-1.7B-Base | aufklarer | 39.0 | low | |
| 8 | PrimeTTS | owensong/Inflect-Nano-v1 | Luigi | 35.0 | medium | |
| 9 | kani-tts-400m-en | nineninesix/kani-tts-400m-0.3-pt | nineninesix | 19.0 | low | |
| 10 | kani-tts-400m-en-GGUF | nineninesix/kani-tts-400m-0.3-pt | Mungert | 19.0 | low | |
| 11 | kani-tts-400m-ky | nineninesix/kani-tts-400m-0.3-pt | nineninesix | 19.0 | low | |
| 12 | Inflect-Micro-v2 | owensong/Inflect-Micro-v2 | owensong | 15.93 | low | |
| 13 | Inflect-Nano-v2 | owensong/Inflect-Nano-v1 | owensong | 15.93 | low | |
| 14 | Inflect-Nano-v2-GGUF | owensong/Inflect-Nano-v2 | remixerdec | 15.93 | low | |
| 15 | Inflect-Micro-v2-GGUF | owensong/Inflect-Micro-v2 | remixerdec | 15.93 | low | |
| 16 | DeepFilterNet3-CoreML | Rikorose/DeepFilterNet3 | aufklarer | 13.0 | low | |
| 17 | JaiTTS-F5TTS | SWivid/F5-TTS | JTS-AI | 11.38 | high | |
| 18 | Voxtral-4B-TTS-2603 | mistralai/Ministral-3-3B-Base-2512 | mistralai | 10.3 | low | |
| 19 | Freya-TTS | — | freyavoice | 10.0 | medium | |
| 20 | kokoro.best | — | inoryQwQ | 10.0 | medium | RTF |
| 21 | TEA-ASR-1 | Qwen/Qwen3-ASR-1.7B | JacobLinCool | 9.1 | high | |
| 22 | AudioCPP-Voxtral-Mini-4B-Realtime-2602-GGUF | — | mistral-experimental | 8.62 | low | |
| 23 | mlx-q6-higgs-tts-3-4b | bosonai/higgs-tts-3-4b | whitelabel | 7.28 | low | |
| 24 | Nemotron-3.5-ASR-Streaming-0.6B-CoreML-INT8 | nvidia/nemotron-3.5-asr-streaming-0.6b | aufklarer | 6.8 | medium | RTF (encode + decode) |
| 25 | Nemotron-3.5-ASR-Streaming-0.6B-CoreML-INT8 | nvidia/nemotron-3.5-asr-streaming-0.6b | playstonex | 6.8 | medium | RTF (encode + decode) |
| 26 | Whisper-Large-v3-Turbo-CoreML | openai/whisper-large-v3-turbo | aufklarer | 6.5 | low | |
| 27 | kazakh-whisper-large-v3-turbo | openai/whisper-large-v3-turbo | shyngys879 | 6.46 | low | |
| 28 | moss-transcribe-diarize-gguf | OpenMOSS-Team/MOSS-Transcribe-Diarize | handy-computer | 6.12 | low | |
| 29 | Omnilingual-ASR-CTC-300M-CoreML-INT8-10s | facebook/omniASR-CTC-300M | aufklarer | 5.6 | low | |
| 30 | Omnilingual-ASR-CTC-300M-MLX-4bit | facebook/omniASR-CTC-300M | aufklarer | 5.6 | low | |
| 31 | azerbaijani-whisper-small | openai/whisper-small | LocalDoc | 5.3 | high | |
| 32 | Nemotron-3.5-ASR-Streaming-0.6B-MLX-8bit | nvidia/nemotron-3.5-asr-streaming-0.6b | aufklarer | 4.85 | medium | Real-time factor |
| 33 | Nemotron-3.5-ASR-Streaming-0.6B-MLX-8bit | nvidia/nemotron-3.5-asr-streaming-0.6b | aufklarer | 4.81 | high | |
| 34 | LocalVQE | LocalAI-io/LocalVQE | LocalAI-io | 4.8 | low | |
| 35 | Nemotron-3.5-ASR-Streaming-0.6B-MLX-5bit | nvidia/nemotron-3.5-asr-streaming-0.6b | aufklarer | 4.67 | medium | Real-time factor |
| 36 | piper-plus-tsukuyomi-chan | ayousanz/piper-plus-base | ayousanz | 4.6 | medium | |
| 37 | Nemotron-3.5-ASR-Streaming-0.6B-MLX-5bit | nvidia/nemotron-3.5-asr-streaming-0.6b | aufklarer | 4.36 | high | |
| 38 | VoxCPM-GGUF | openbmb/VoxCPM1.5 | bluryar | 3.61 | medium | |
| 39 | azerbaijani-whisper-turbo | openai/whisper-large-v3-turbo | LocalDoc | 3.3 | low | |
| 40 | batisay-ko-turbo | openai/whisper-large-v3-turbo | batiai | 2.8 | low | |
| 41 | Cosmos3-Edge-Policy-DROID | nvidia/Cosmos3-Edge-Policy-DROID | nvidia | 2.47 | low | |
| 42 | VibeVoice-ASR-BitNet | microsoft/VibeVoice-ASR-BitNet | microsoft | 1.98 | medium | RTF |
| 43 | moonshine-base-bn | UsefulSensors/moonshine-base | Sanjidh090 | 1.2 | low | |
| 44 | mlx-indextts2-standard-fp16 | — | vanch007 | 1.13 | low | |
| 45 | mlx-indextts2-standard-8bit | — | vanch007 | 1.13 | low | |
| 46 | LocalVQE-v1.4-AEC-200K-CoreML | LocalAI-io/LocalVQE | aufklarer | 1.11 | low | |
| 47 | FlashSR-MLX-4bit | jakeoneijk/FlashSR_Inference | aufklarer | 1.1 | medium | Real-time factor (wall / audio) |
| 48 | Nos_ASR-wav2vec2-xls-r-300m-gl | facebook/wav2vec2-xls-r-300m | proxectonos | 0.85 | low | |
| 49 | w2v-xls-r-uk | facebook/wav2vec2-xls-r-300m | Yehor | 0.38 | medium | |
| 50 | diar_streaming_sortformer_4spk-v2.1 | nvidia/diar_streaming_sortformer_4spk-v2.1 | nvidia | 0.2 | low | |
| 51 | diar_streaming_sortformer_4spk-v2 | nvidia/diar_streaming_sortformer_4spk-v2 | nvidia | 0.2 | low | |