All Models and Download URLs

To keep the software package size small, no models are bundled. They are downloaded automatically on first use from HuggingFace, the Chinese mirror site hf-mirror.com, and Alibaba ModelScope modelscope.cn.

Models are generally large. The overseas model repository is not directly accessible from mainland China — a VPN may be needed. Without a VPN, the software will automatically switch to domestic mirror sites.

Even with a VPN, unstable connections may still cause download failures.

Domestic mirror sites have download frequency limits and may not be fast or stable enough.

Due to the above factors, download failures are common, and many other errors are indirectly caused by failed model downloads.

This page lists all model download URLs and local storage paths. If automatic download keeps failing, delete any partially downloaded model files and try manual download.

• Overseas model repository: https://huggingface.co
• Some Alibaba models and ONNX models are downloaded from ModelScope: https://modelscope.cn

Download Notes

Most models consist of multiple files, and different models may share file names (e.g., model.safetensors). If a file with the same name already exists in the download directory, the browser may auto-rename it (e.g., model(2).safetensors). You must rename it back to the original name and place it in the correct directory for the software to recognize it.

On the huggingface.co website, click the download icon to download the model file.

Speech Recognition Models

Qwen-ASR (Built-in)

0.6B Model:

• URL: https://huggingface.co/Qwen/Qwen3-ASR-0.6B/tree/main
• Path: app_dir/models/models--Qwen--Qwen3-ASR-0.6B

1.7B Model:

• URL: https://huggingface.co/Qwen/Qwen3-ASR-1.7B/tree/main
• Path: app_dir/models/models--Qwen--Qwen3-ASR-1.7B

Firered Chinese (Built-in)

• URL: https://modelscope.cn/models/himyworld/videotrans/resolve/master/fireredasr2aed.zip
• Path: app_dir/models/ — extract the fireredasr folder from the zip to here

Dolphin (Built-in)

• URL: https://modelscope.cn/models/himyworld/videotrans/resolve/master/dolphin.zip
• Path: app_dir/models/ — extract the dolphin folder to here

Omnilingual (Built-in)

• URL: https://modelscope.cn/models/himyworld/videotrans/resolve/master/omnilingual.zip
• Path: app_dir/models/ — extract the omnilingual folder to here

Parakeet Japanese (Built-in)

• URL: https://modelscope.cn/models/himyworld/videotrans/resolve/master/parakeet-ja.zip
• Path: app_dir/models/ — extract the parakeet folder to here

faster-whisper (Built-in)

Model	Local Path	Download URL
tiny	app_dir/models/models--Systran--faster-whisper-tiny	https://huggingface.co/Systran/faster-whisper-tiny/tree/main
base	app_dir/models/models--Systran--faster-whisper-base	https://huggingface.co/Systran/faster-whisper-base/tree/main
small	app_dir/models/models--Systran--faster-whisper-small	https://huggingface.co/Systran/faster-whisper-small/tree/main
medium	app_dir/models/models--Systran--faster-whisper-medium	https://huggingface.co/Systran/faster-whisper-medium/tree/main
large-v1	app_dir/models/models--Systran--faster-whisper-large-v1	https://huggingface.co/Systran/faster-whisper-large-v1/tree/main
large-v2	app_dir/models/models--Systran--faster-whisper-large-v2	https://huggingface.co/Systran/faster-whisper-large-v2/tree/main
large-v3	app_dir/models/models--Systran--faster-whisper-large-v3	https://huggingface.co/Systran/faster-whisper-large-v3/tree/main
large-v3-turbo	app_dir/models/models--mobiuslabsgmbh--faster-whisper-large-v3-turbo	https://huggingface.co/mobiuslabsgmbh/faster-whisper-large-v3-turbo/tree/main
tiny.en	app_dir/models/models--Systran--faster-whisper-tiny.en	https://huggingface.co/Systran/faster-whisper-tiny.en/tree/main
base.en	app_dir/models/models--Systran--faster-whisper-base.en	https://huggingface.co/Systran/faster-whisper-base.en/tree/main
small.en	app_dir/models/models--Systran--faster-whisper-small.en	https://huggingface.co/Systran/faster-whisper-small.en/tree/main
medium.en	app_dir/models/models--Systran--faster-whisper-medium.en	https://huggingface.co/Systran/faster-whisper-medium.en/tree/main
distil-large-v2	app_dir/models/models--Systran--faster-distil-whisper-large-v2	https://huggingface.co/Systran/faster-distil-whisper-large-v2/tree/main
distil-large-v3	app_dir/models/models--Systran--faster-distil-whisper-large-v3	https://huggingface.co/Systran/faster-distil-whisper-large-v3/tree/main
distil-large-v3.5	app_dir/models/models--distil-whisper--distil-large-v3.5-ct2	https://huggingface.co/distil-whisper/distil-large-v3.5-ct2/tree/main
distil-small.en	app_dir/models/models--Systran--faster-distil-whisper-small.en	https://huggingface.co/Systran/faster-distil-whisper-small.en/tree/main
distil-medium.en	app_dir/models/models--Systran--faster-distil-whisper-medium.en	https://huggingface.co/Systran/faster-distil-whisper-medium.en/tree/main

openai-whisper (Built-in)

Place downloaded .pt model files directly in app_dir/models/

• tiny.en https://openaipublic.azureedge.net/main/whisper/models/d3dd57d32accea0b295c96e26691aa14d8822fac7d9d27d5dc00b4ca2826dd03/tiny.en.pt
• tiny https://openaipublic.azureedge.net/main/whisper/models/65147644a518d12f04e32d6f3b26facc3f8dd46e5390956a9424a650c0ce22b9/tiny.pt
• base.en https://openaipublic.azureedge.net/main/whisper/models/25a8566e1d0c1e2231d1c762132cd20e0f96a85d16145c3a00adf5d1ac670ead/base.en.pt
• base https://openaipublic.azureedge.net/main/whisper/models/ed3a0b6b1c0edf879ad9b11b1af5a0e6ab5db9205f891f668f8b0e6c6326e34e/base.pt
• small.en https://openaipublic.azureedge.net/main/whisper/models/f953ad0fd29cacd07d5a9eda5624af0f6bcf2258be67c92b79389873d91e0872/small.en.pt
• small https://openaipublic.azureedge.net/main/whisper/models/9ecf779972d90ba49c06d968637d720dd632c55bbf19d441fb42bf17a411e794/small.pt
• medium.en https://openaipublic.azureedge.net/main/whisper/models/d7440d1dc186f76616474e0ff0b3b6b879abc9d1a4926b7adfa41db2d497ab4f/medium.en.pt
• medium https://openaipublic.azureedge.net/main/whisper/models/345ae4da62f9b3d59415adc60127b97c714f32e89e936602e85993674d08dcb1/medium.pt
• large-v1 https://openaipublic.azureedge.net/main/whisper/models/e4b87e7e0bf463eb8e6956e646f1e277e901512310def2c24bf0e11bd3c28e9a/large-v1.pt
• large-v2 https://openaipublic.azureedge.net/main/whisper/models/81f7c96c852ee8fc832187b0132e569d6c3065a3252ed18e56effd0b6a73e524/large-v2.pt
• large-v3 https://openaipublic.azureedge.net/main/whisper/models/e5b1a55b89c1367dacf97e3e19bfd829a01529dbfdeefa8caeb59b3f1b81dadb/large-v3.pt
• large https://openaipublic.azureedge.net/main/whisper/models/e5b1a55b89c1367dacf97e3e19bfd829a01529dbfdeefa8caeb59b3f1b81dadb/large-v3.pt
• large-v3-turbo https://openaipublic.azureedge.net/main/whisper/models/aff26ae408abcba5fbf8813c21e62b0941638c5f6eebfb145be0c9839262a19a/large-v3-turbo.pt
• turbo https://openaipublic.azureedge.net/main/whisper/models/aff26ae408abcba5fbf8813c21e62b0941638c5f6eebfb145be0c9839262a19a/large-v3-turbo.pt

HuggingFace_ASR (Built-in)

• zai-org/GLM-ASR-Nano-2512

  • URL: https://huggingface.co/zai-org/GLM-ASR-Nano-2512/tree/main
  • Path: app_dir/models/models--zai-org--GLM-ASR-Nano-2512

• anke01/whisper-small-uyghur

  • URL: https://huggingface.co/anke01/whisper-small-uyghur/tree/main
  • Path: app_dir/models/models--anke01--whisper-small-uyghur

• nvidia/parakeet-ctc-1.1b (English)

  • URL: https://huggingface.co/nvidia/parakeet-ctc-1.1b/tree/main
  • Path: app_dir/models/models--nvidia--parakeet-ctc-1.1b

• reazon-research/japanese-wav2vec2-large-rs35kh (Japanese)

  • URL: https://huggingface.co/reazon-research/japanese-wav2vec2-large-rs35kh/tree/main
  • Path: app_dir/models/models--reazon-research--japanese-wav2vec2-large-rs35kh

• kotoba-tech/kotoba-whisper-v2.0 (Japanese)

  • URL: https://huggingface.co/kotoba-tech/kotoba-whisper-v2.0/tree/main
  • Path: app_dir/models/models--kotoba-tech--kotoba-whisper-v2.0

• biodatlab/whisper-th-large-v3 (Thai)

  • URL: https://huggingface.co/biodatlab/whisper-th-large-v3/tree/main
  • Path: app_dir/models/models--biodatlab--whisper-th-large-v3

• vinai/Phowhisper-large (Vietnamese)

  • URL: https://huggingface.co/vinai/Phowhisper-large/tree/main
  • Path: app_dir/models/models--vinai--Phowhisper-large

• openai/whisper-large-v3

  • URL: https://huggingface.co/openai/whisper-large-v3/tree/main
  • Path: app_dir/models/models--openai--whisper-large-v3

whisper.cpp

• Windows pre-compiled package: After downloading, copy the whisper-cli folder to your app directory.
  • https://huggingface.co/mortimerme/repocollect/resolve/main/whisper-cpp-win32.zip?download=true
  • https://modelscope.cn/models/himyworld/videotrans/resolve/master/whisper-cpp-win32.zip
• Model download URLs:
  • Primary source: https://huggingface.co/ggerganov/whisper.cpp/tree/main
  • Mirror: https://hf-mirror.com/ggerganov/whisper.cpp/tree/main

Single-file models. Place the .bin file in app_dir/models/.

---

Translation Models (Subtitle Translation)

Hy-MT2-1.8B (Built-in)

• URL: https://huggingface.co/tencent/Hy-MT2-1.8B/tree/main
• Path: app_dir/models/models--tencent--Hy-MT2-1.8B

M2M100 (Built-in)

• URL: https://modelscope.cn/models/himyworld/videotrans/resolve/master/m2m100_12b_model.zip
• Path: app_dir/models/ — extract the m2m100_12b folder to here

---

TTS Models

Piper (Built-in)

• URL: https://huggingface.co/rhasspy/piper-voices/tree/main
• Path: app_dir/models/piper

VITS (Built-in)

• URL: https://modelscope.cn/models/himyworld/videotrans/resolve/master/vits-tts.zip
• Path: app_dir/models/ — extract the vits folder to here

ZipVoice (Built-in)

• URL: https://modelscope.cn/models/himyworld/videotrans/resolve/master/zipvoice-tts.zip
• Path: app_dir/models/ — extract the zipvoice folder to here

OmniVoice (Built-in)

• URL: https://huggingface.co/k2-fsa/OmniVoice/tree/main
• Path: app_dir/models/models--k2-fsa--OmniVoice

MOSS-TTS-Nano (Built-in)

• URL: https://huggingface.co/OpenMOSS-Team/MOSS-TTS-Nano-100M/tree/main
• Path: app_dir/models/MOSS-TTS-Nano-100M
• URL: https://huggingface.co/OpenMOSS-Team/MOSS-Audio-Tokenizer-Nano-ONNX/tree/main
• Path: app_dir/models/MOSS-Audio-Tokenizer-Nano-ONNX

ChatterBox (Built-in)

• URL: https://huggingface.co/ResembleAI/chatterbox/tree/main
• Path: app_dir/models/models--ResembleAI--chatterbox

Supertonic (Built-in)

• URL: https://huggingface.co/Supertone/supertonic-3/tree/main
• Path: app_dir/models/models--Supertone--supertonic-3

Qwen3-TTS (Built-in)

• URL: https://huggingface.co/Qwen/Qwen3-TTS-12Hz-0.6B-Base/tree/main

• Path: app_dir/models/models--Qwen--Qwen3-TTS-12Hz-0.6B-Base

• URL: https://huggingface.co/Qwen/Qwen3-TTS-12Hz-0.6B-CustomVoice/tree/main

• Path: app_dir/models/models--Qwen--Qwen3-TTS-12Hz-0.6B-CustomVoice

Confucius-TTS (Built-in)

• URL: https://huggingface.co/netease-youdao/Confucius4-TTS/tree/main

• Path: app_dir/models/models--netease-youdao--Confucius4-TTS

• URL: https://huggingface.co/facebook/w2v-bert-2.0/tree/main

• Path: app_dir/models/models--models--facebook--w2v-bert-2.0

• URL: https://huggingface.co/nvidia/bigvgan_v2_22khz_80band_256x/tree/main

• Path: app_dir/models/models--nvidia--bigvgan_v2_22khz_80band_256x

• URL: https://huggingface.co/funasr/campplus/tree/main

• Path: app_dir/models/models--funasr--campplus

F5-TTS (Built-in)

• Official Chinese-English model (1.35G): https://huggingface.co/SWivid/F5-TTS/tree/main/F5TTS_v1_Base

Path: app_dir/models/models--SWivid--F5-TTS/F5TTS_v1_Base

• Japanese model (5.6G): https://huggingface.co/Jmica/F5TTS/tree/main/JA_21999120

Path: app_dir/models/models--Jmica--F5TTS/JA_21999120

• French model (5.4G): https://huggingface.co/RASPIAUDIO/F5-French-MixedSpeakers-reduced/tree/main

Path: app_dir/models/models--RASPIAUDIO--F5-French-MixedSpeakers-reduced

• German model (1.35G): https://huggingface.co/hvoss-techfak/F5-TTS-German/tree/main

Path: app_dir/models/models--hvoss-techfak--F5-TTS-German

• Russian model (3.4G): https://huggingface.co/hotstone228/F5-TTS-Russian/tree/main

Path: app_dir/models/models--hotstone228--F5-TTS-Russian

• Italian model (1.35G): https://huggingface.co/alien79/F5-TTS-italian/tree/main

Path: app_dir/models/models--alien79--F5-TTS-italian

• Spanish model (5.4G): https://huggingface.co/jpgallegoar/F5-Spanish/tree/main

Path: app_dir/models/models--jpgallegoar--F5-Spanish

• Hindi model (2.5G): https://huggingface.co/SPRINGLab/F5-Hindi-24KHz/tree/main

Path: app_dir/models/models--SPRINGLab/F5-Hindi-24KHz

• Arabic model (2.6G): https://huggingface.co/silma-ai/silma-tts/tree/main

Path: app_dir/models/models--silma-ai--silma-tts

---

Speaker Diarization Models

Built-in Model

• URL: https://modelscope.cn/models/himyworld/videotrans/tree/master/onnx

Download these 3 files from the URL above: 3dspeaker_speech_eres2net_large_sv_zh-cn_3dspeaker_16k.onnx, nemo_en_titanet_small.onnx, seg_model.onnx

• Path: app_dir/models/onnx/ — place the 3 downloaded files here.

Reverb

• URL: https://huggingface.co/Revai/reverb-diarization-v1
• Path: app_dir/models/models--Revai--reverb-diarization-v1

pyannote

• URL: https://huggingface.co/pyannote/speaker-diarization-3.1
• Path: app_dir/models/models--pyannote--speaker-diarization-3.1

Ali CAM++

• URL: https://modelscope.cn/models/iic/speech_campplus_speaker-diarization_common
• Path: app_dir/models/speech_campplus_speaker-diarization_common

Vocal/Background Separation, Noise Reduction, Punctuation Restoration Models

URL: https://modelscope.cn/models/himyworld/videotrans/tree/master/onnx Path: Download all .onnx files from this page and place them in app_dir/models/onnx/.

Real-time Speech Recognition Model

• URL: https://modelscope.cn/models/himyworld/videotrans/resolve/master/realtimestt.zip
• Path: After downloading, extract the zip — you will see an onnx folder. Copy all files from it to app_dir/models/onnx/.