Top open audio models
Audio models for speech recognition, generation, and audio processing.
How this list works: ranked by Hugging Face downloads in the last 30 days, among models with 1,000+ downloads.
| # | Model | Author | Downloads (30 days) | Likes | Size | License | Commercial use | Runs on |
|---|---|---|---|---|---|---|---|---|
| 1 | wav2vec2-large-xlsr-53-japanese | jonatasgrosman | 15.8M | 108 | – | Apache 2.0 | Yes | GPU |
| 2 | whisperkit-coreml | argmaxinc | 12M | 251 | – | MIT | Yes | CPU or GPU |
| 3 | Kokoro-82M | hexgrad | 10.5M | 7.3K | 82M | Apache 2.0 | Yes | CPU or GPU |
| 4 | clap-htsat-fused | laion | 7.4M | 165 | – | Apache 2.0 | Yes | GPU |
| 5 | speaker-diarization-3.1 | pyannote | 6.8M | 4.5K | – | MIT | Yes | CPU or GPU |
| 6 | audio.cpp-gguf | audio-cpp | 6.4M | 255 | – | Custom (other) | Check the license | CPU |
| 7 | XTTS-v2 | coqui | 6.3M | 3.9K | – | Custom (other) | Check the license | CPU or GPU |
| 8 | whisper-large-v3-turbo | openai | 6.1M | 3.5K | – | MIT | Yes | GPU |
| 9 | speaker-diarization-community-1 | pyannote | 5.1M | 3.1K | – | CC BY 4.0 | Yes, with conditions | CPU or GPU |
| 10 | faster-whisper-small | Systran | 4.6M | 73 | – | MIT | Yes | CPU or GPU |
| 11 | wav2vec2-large-xlsr-53-portuguese | jonatasgrosman | 4.5M | 69 | – | Apache 2.0 | Yes | GPU |
| 12 | YuE2-GGUF | Serveurperso | 4.3M | 19 | – | CC BY-NC 4.0 | No | CPU |
| 13 | wav2vec2-large-xlsr-53-russian | jonatasgrosman | 4.2M | 85 | – | Apache 2.0 | Yes | GPU |
| 14 | whisper-large-v3 | openai | 3.8M | 6.7K | – | Apache 2.0 | Yes | GPU |
| 15 | whisper-small | openai | 3.5M | 632 | – | Apache 2.0 | Yes | GPU |
| 16 | wav2vec2-large-xlsr-53-polish | jonatasgrosman | 3M | 21 | – | Apache 2.0 | Yes | GPU |
| 17 | parakeet-tdt-0.6b-v3 | mlx-community | 2.5M | 67 | 600M | CC BY 4.0 | Yes, with conditions | CPU |
| 18 | wav2vec2-large-xlsr-53-dutch | jonatasgrosman | 2.5M | 24 | – | Apache 2.0 | Yes | GPU |
| 19 | mms-300m-1130-forced-aligner | MahmoudAshraf | 2.4M | 116 | 300M | CC BY-NC 4.0 | No | GPU |
| 20 | faster-whisper-tiny | Systran | 2.3M | 32 | – | MIT | Yes | CPU or GPU |
| 21 | wav2vec2-large-robust-24-ft-age-gender | audeering | 2.3M | 79 | – | CC BY-NC-SA 4.0 | No | GPU |
| 22 | wav2vec2-large-xlsr-53-greek | jonatasgrosman | 2.2M | 10 | – | Apache 2.0 | Yes | GPU |
| 23 | wav2vec2-large-xlsr-53-arabic | jonatasgrosman | 2.2M | 64 | – | Apache 2.0 | Yes | GPU |
| 24 | wav2vec2-indonesian-javanese-sundanese | indonesian-nlp | 2.1M | 21 | – | Apache 2.0 | Yes | GPU |
| 25 | Qwen3-TTS-12Hz-1.7B-CustomVoice | Qwen | 2.1M | 2.1K | 1.7B | Apache 2.0 | Yes | GPU |
Other model comparisons
Top open language modelsTop open image modelsTop open video modelsTop open embedding modelsTop open multimodal modelsTop open text-generation models (LLMs)Top open text-to-image modelsTop open text-to-speech modelsTop open speech-recognition modelsTop open feature-extraction modelsTop open sentence-similarity modelsTop open image-to-text modelsTop open vision-language modelsTop open image-classification modelsTop open image-segmentation modelsTop open object-detection modelsTop open depth-estimation modelsTop open audio-classification modelsTop open video-classification models