Local audio models
Speak, transcribe, convert audio, music and sound effects.
Documented GPU memory
Lowest published path per model · GB, log scale · lower is better · 31 of 168 models
- Color = publisher
Source: publishers' documented requirements
Word error rate · Open ASR
0–8% · lower is better · published results, not local measurements
Source: open-asr-en-shortform · checked Oct 20, 2026
whisper-base: 1 GB
168 models · 31 with documented memory
25 models list Portuguese
Choose your machine and the charts and tables mark what fits in its memory.
Audio models
| Nemotron-3-Diarization | 0.1 | No publisher documents a memory path for this model | Neither the Hub card nor the publisher's pages name its languages | Sep 2026 | OpenMDW 1.1 |
|---|---|---|---|---|---|
| AuK | 1.5 | 25 | Neither the Hub card nor the publisher's pages name its languages | Sep 2026 | MIT |
| AuK-Flash | The Hub reports no parameter count for this repository | 24.97 | 2 | Sep 2026 | MIT |
| VibeVoice-ASR-Streaming-7B | 8.7 | No publisher documents a memory path for this model | 10 · PT | Sep 2026 | MIT |
| Breeze TTS 2 | 3.47 | 12 | 2 | Aug 2026 | BreezeBlue Research and Non-Commercial |
| granite-speech-5.0-470m-turboctc | 0.5 | No publisher documents a memory path for this model | 1 | Aug 2026 | Apache 2.0 |
| granite-speech-5.0-470m-turboctc-nc | 0.5 | No publisher documents a memory path for this model | 1 | Aug 2026 | CC BY-NC-SA 4.0 |
| VibeVoice-ASR-BitNet | 0.3 | No publisher documents a memory path for this model | 7 · PT | Jul 2026 | MIT |
| Qwen3-ASR-0.6B-hf | 0.8 | No publisher documents a memory path for this model | 30 · PT | Jun 2026 | Apache 2.0 |
| Qwen3-ASR-1.7B-hf | 2 | No publisher documents a memory path for this model | 30 · PT | Jun 2026 | Apache 2.0 |
| Higgs Audio V3 TTS | 4 | 16 | 100 · PT | Jun 2026 | Boson Higgs TTS 3 Research and Non-Commercial |
| granite-speech-4.1-2b | 2.3 | No publisher documents a memory path for this model | 6 · PT | Apr 2026 | Apache 2.0 |
| granite-speech-4.1-2b-plus | 2.1 | No publisher documents a memory path for this model | 5 · PT | Apr 2026 | Apache 2.0 |
| Voxtral TTS | 4 | 16 | 9 · PT | Mar 2026 | CC BY-NC 4.0 |
| Fish Audio S2 Pro | 4 | 24 | 83 · PT | Mar 2026 | Fish Audio Research |
| VibeVoice-ASR | 8.7 | No publisher documents a memory path for this model | 51 · PT | Jan 2026 | MIT |
| Magpie-Multilingual 357M | 0.364 | No publisher documents a memory path for this model | 12 · PT | Jan 2026 | NVIDIA Open Model |
| GLM-TTS | The Hub reports no parameter count for this repository | No publisher documents a memory path for this model | 2 | Dec 2025 | MIT |
| Step Audio EditX (Mar 2026) | 3 | 12 | 5 | Nov 2025 | Publisher terms |
| VibeVoice 1.5B | 1.5 | No publisher documents a memory path for this model | 2 | Aug 2025 | MIT |
| parakeet-tdt-0.6b-v3 | 0.6 | 2 | Neither the Hub card nor the publisher's pages name its languages | Aug 2025 | CC BY 4.0 |
| OpenAudio S1 Mini | 0.5 | 12 | 13 · PT | Jun 2025 | CC BY-NC-SA 4.0 |
| Chatterbox | 0.5 | No publisher documents a memory path for this model | 1 | May 2025 | MIT |
| Stable Audio Open Small | 0.5 | No publisher documents a memory path for this model | 1 | May 2025 | Stability AI Community |
24 of 126
42 more repositories with limited data
| Ace-Step1.5 | Neither the Hub card nor the publisher's pages name its languages | MIT |
|---|---|---|
| bark | Neither the Hub card nor the publisher's pages name its languages | MIT |
| chatterbox | Neither the Hub card nor the publisher's pages name its languages | MIT |
| chatterbox-turbo-ONNX | Neither the Hub card nor the publisher's pages name its languages | MIT |
| ChatTTS | Neither the Hub card nor the publisher's pages name its languages | CC BY-NC 4.0 |
| Confucius4-R2T2-8bit | 2 | Publisher terms |
| CosyVoice2-0.5B | Neither the Hub card nor the publisher's pages name its languages | Apache 2.0 |
| Dramabox | Neither the Hub card nor the publisher's pages name its languages | Publisher terms |
| E2-TTS | Neither the Hub card nor the publisher's pages name its languages | CC BY-NC 4.0 |
| F5-TTS | Neither the Hub card nor the publisher's pages name its languages | CC BY-NC 4.0 |
| faster-whisper-large-v3 | Neither the Hub card nor the publisher's pages name its languages | MIT |
| faster-whisper-small | Neither the Hub card nor the publisher's pages name its languages | MIT |
| fish-speech-1.5 | Neither the Hub card nor the publisher's pages name its languages | CC BY-NC-SA 4.0 |
| Fun-CosyVoice3-0.5B-2512 | Neither the Hub card nor the publisher's pages name its languages | Apache 2.0 |
| HunyuanVideo-Foley | Neither the Hub card nor the publisher's pages name its languages | Publisher terms |
| IndexTTS-2 | Neither the Hub card nor the publisher's pages name its languages | Not stated |
| IndexTTS-2.5 | Neither the Hub card nor the publisher's pages name its languages | Publisher terms |
| indic-conformer-600m-multilingual | Neither the Hub card nor the publisher's pages name its languages | MIT |
| kitten-tts-2 | Neither the Hub card nor the publisher's pages name its languages | Publisher terms |
| LTX-2.3-22b-LoRA-Foley-V2A | 1 | Publisher terms |
| magenta-realtime-2 | Neither the Hub card nor the publisher's pages name its languages | CC BY 4.0 |
| MaskGCT | Neither the Hub card nor the publisher's pages name its languages | CC BY-NC 4.0 |
| MeloTTS-English | Neither the Hub card nor the publisher's pages name its languages | MIT |
| mms-tts-eng | Neither the Hub card nor the publisher's pages name its languages | CC BY-NC 4.0 |
24 of 42