Skip to content
Local AI Wizard
Your machine
Theme

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

Lowest documented memory

whisper-base: 1 GB

Catalog

168 models · 31 with documented memory

Portuguese

25 models list Portuguese

Choose your machine and the charts and tables mark what fits in its memory.

Audio models

168 models · 17 reviewed · checking Sep 26, 2026 

Audio models
Nemotron-3-DiarizationMLX Community · Classify audio / voice detection · OpenMDW 1.10.1No publisher documents a memory path for this modelNeither the Hub card nor the publisher's pages name its languagesSep 2026OpenMDW 1.1
AuKTencent · Text to speech (TTS) · MIT1.525Neither the Hub card nor the publisher's pages name its languagesSep 2026MIT
AuK-FlashTencent · Text to speech (TTS) · MITThe Hub reports no parameter count for this repository24.972Sep 2026MIT
VibeVoice-ASR-Streaming-7BMicrosoft · Speech to text · MIT8.7No publisher documents a memory path for this model10 · PTSep 2026MIT
Breeze TTS 2BreezeBlue · Text to speech (TTS) · BreezeBlue Research and Non-Commercial3.47122Aug 2026BreezeBlue Research and Non-Commercial
granite-speech-5.0-470m-turboctcIBM · Speech to text · Apache 2.00.5No publisher documents a memory path for this model1Aug 2026Apache 2.0
granite-speech-5.0-470m-turboctc-ncIBM · Speech to text · CC BY-NC-SA 4.00.5No publisher documents a memory path for this model1Aug 2026CC BY-NC-SA 4.0
VibeVoice-ASR-BitNetMicrosoft · Speech to text · MIT0.3No publisher documents a memory path for this model7 · PTJul 2026MIT
Qwen3-ASR-0.6B-hfAlibaba · Speech to text · Apache 2.00.8No publisher documents a memory path for this model30 · PTJun 2026Apache 2.0
Qwen3-ASR-1.7B-hfAlibaba · Speech to text · Apache 2.02No publisher documents a memory path for this model30 · PTJun 2026Apache 2.0
Higgs Audio V3 TTSBoson AI · Text to speech (TTS) · Boson Higgs TTS 3 Research and Non-Commercial416100 · PTJun 2026Boson Higgs TTS 3 Research and Non-Commercial
granite-speech-4.1-2bIBM · Speech to text · Apache 2.02.3No publisher documents a memory path for this model6 · PTApr 2026Apache 2.0
granite-speech-4.1-2b-plusIBM · Speech to text · Apache 2.02.1No publisher documents a memory path for this model5 · PTApr 2026Apache 2.0
Voxtral TTSMistral · Text to speech (TTS) · CC BY-NC 4.04169 · PTMar 2026CC BY-NC 4.0
Fish Audio S2 ProFish Audio · Text to speech (TTS) · Fish Audio Research42483 · PTMar 2026Fish Audio Research
VibeVoice-ASRMicrosoft · Speech to text · MIT8.7No publisher documents a memory path for this model51 · PTJan 2026MIT
Magpie-Multilingual 357MNVIDIA · Text to speech (TTS) · NVIDIA Open Model0.364No publisher documents a memory path for this model12 · PTJan 2026NVIDIA Open Model
GLM-TTSZ.ai · Text to speech (TTS) · MITThe Hub reports no parameter count for this repositoryNo publisher documents a memory path for this model2Dec 2025MIT
Step Audio EditX (Mar 2026)StepFun · Text to speech (TTS) · Publisher terms3125Nov 2025Publisher terms
VibeVoice 1.5BMicrosoft · Text to speech (TTS) · MIT1.5No publisher documents a memory path for this model2Aug 2025MIT
parakeet-tdt-0.6b-v3NVIDIA · Speech to text · CC BY 4.00.62Neither the Hub card nor the publisher's pages name its languagesAug 2025CC BY 4.0
OpenAudio S1 MiniFish Audio · Text to speech (TTS) · CC BY-NC-SA 4.00.51213 · PTJun 2025CC BY-NC-SA 4.0
ChatterboxResemble AI · Text to speech (TTS) · MIT0.5No publisher documents a memory path for this model1May 2025MIT
Stable Audio Open SmallStability AI · Sound effects and audio · Stability AI Community0.5No publisher documents a memory path for this model1May 2025Stability AI Community
24 of 126
42 more repositories with limited datano parameters, documented memory or release date
Audio repositories with limited data
Ace-Step1.5ACE-Step · Sound effects and audio · MITNeither the Hub card nor the publisher's pages name its languagesMIT
barkSuno · Text to speech (TTS) · MITNeither the Hub card nor the publisher's pages name its languagesMIT
chatterboxResemble AI · Text to speech (TTS) · MITNeither the Hub card nor the publisher's pages name its languagesMIT
chatterbox-turbo-ONNXResemble AI · Text to speech (TTS) · MITNeither the Hub card nor the publisher's pages name its languagesMIT
ChatTTS2Noise · Sound effects and audio · CC BY-NC 4.0Neither the Hub card nor the publisher's pages name its languagesCC BY-NC 4.0
Confucius4-R2T2-8bitMLX Community · Speech to text · Publisher terms2Publisher terms
CosyVoice2-0.5BQwenAudio · Text to speech (TTS) · Apache 2.0Neither the Hub card nor the publisher's pages name its languagesApache 2.0
DramaboxResemble AI · Text to speech (TTS) · Publisher termsNeither the Hub card nor the publisher's pages name its languagesPublisher terms
E2-TTSSWivid · Text to speech (TTS) · CC BY-NC 4.0Neither the Hub card nor the publisher's pages name its languagesCC BY-NC 4.0
F5-TTSSWivid · Text to speech (TTS) · CC BY-NC 4.0Neither the Hub card nor the publisher's pages name its languagesCC BY-NC 4.0
faster-whisper-large-v3SYSTRAN · Speech to text · MITNeither the Hub card nor the publisher's pages name its languagesMIT
faster-whisper-smallSYSTRAN · Speech to text · MITNeither the Hub card nor the publisher's pages name its languagesMIT
fish-speech-1.5Fish Audio · Text to speech (TTS) · CC BY-NC-SA 4.0Neither the Hub card nor the publisher's pages name its languagesCC BY-NC-SA 4.0
Fun-CosyVoice3-0.5B-2512QwenAudio · Text to speech (TTS) · Apache 2.0Neither the Hub card nor the publisher's pages name its languagesApache 2.0
HunyuanVideo-FoleyTencent · Sound effects and audio · Publisher termsNeither the Hub card nor the publisher's pages name its languagesPublisher terms
IndexTTS-2Index Team · Text to speech (TTS) · Not statedNeither the Hub card nor the publisher's pages name its languagesNot stated
IndexTTS-2.5Index Team · Text to speech (TTS) · Publisher termsNeither the Hub card nor the publisher's pages name its languagesPublisher terms
indic-conformer-600m-multilingualAI4Bharat · Speech to text · MITNeither the Hub card nor the publisher's pages name its languagesMIT
kitten-tts-2KittenML · Text to speech (TTS) · Publisher termsNeither the Hub card nor the publisher's pages name its languagesPublisher terms
LTX-2.3-22b-LoRA-Foley-V2ALightricks · Sound effects and audio · Publisher terms1Publisher terms
magenta-realtime-2Google · Sound effects and audio · CC BY 4.0Neither the Hub card nor the publisher's pages name its languagesCC BY 4.0
MaskGCTAmphion · Text to speech (TTS) · CC BY-NC 4.0Neither the Hub card nor the publisher's pages name its languagesCC BY-NC 4.0
MeloTTS-EnglishOpenVoice · Text to speech (TTS) · MITNeither the Hub card nor the publisher's pages name its languagesMIT
mms-tts-engMeta · Text to speech (TTS) · CC BY-NC 4.0Neither the Hub card nor the publisher's pages name its languagesCC BY-NC 4.0
24 of 42