From a67483dd50372fd765ca21c71d5616ffc880d069 Mon Sep 17 00:00:00 2001 From: Warren B Date: Fri, 4 Sep 2026 19:32:17 +0100 Subject: [PATCH] webui: point every catalog entry at the package it installs 65 of the 90 catalog entries name a download_id that is not a packages[].id, a path no package installs into, or both: 51 unresolvable ids and 14 paths that are not the package's target_directory. This corrects the 60 that can be corrected. They resolve only through a compatibility shim in catalog.ts that strips precision suffixes and guesses; where the guess fails the entry offers no install button at all. Each entry now names the package that entry already meant and the directory that package installs into: - download_id is an exact packages[].id from the entry's own family. Where the old id was a stem ("omnivoice", "chatterbox"), it becomes the family's recommended package. Where it named a variant ("qwen3_tts_1_7b_custom_ voice", "dots_tts_mf_q8_0"), the variant is preserved and only the spelling is corrected to the published id. - path is models/ of that package. 40 entries pointed at pre-GGUF directories that no package writes ("models/chatterbox" -> "models/Chatterbox-GGUF"), and several pointed at a single .gguf file inside the directory, which only resolves when that exact filename ships. - Three entries resolved to safetensors packages the native manager cannot install, so they had no install choice; they now use their family's recommended GGUF package. No entry is added, removed or retasked here, and display names, tasks, modes and min_vram_gb are untouched. The voxcpm1 download_id fixed in #424 is left as it is. The five breeze_tts, cosyvoice3 and chatterbox_turbo entries added since are left alone: those families have no model_specs/*.json yet, so their package ids exist nowhere to point at. They are the 5 that remain unresolvable below, and they resolve themselves once those specs land. Validation: - Entries whose download_id is not a packages[].id, or whose path is not that package's target_directory: 65 before, 5 after -- the 5 being the new families that have no spec yet. - No path is targeted by more than one download_id, so a catalog install leaves one package per directory. - tools/check_loader_catalog_sync.py reports loaders, model_specs and model_manager_v2 in sync. - Directory paths load exactly as the file paths they replace. Same server, same input, audiosr registered twice: models/AudioSR-GGUF 200 models/AudioSR-GGUF/audiosr-basic-f32.gguf 200 identical response fields from both. Co-Authored-By: Claude Opus 5 (1M context) --- webui/configs/models_catalog.json | 120 +++++++++++++++--------------- 1 file changed, 60 insertions(+), 60 deletions(-) diff --git a/webui/configs/models_catalog.json b/webui/configs/models_catalog.json index fb2cbf83..014181b6 100644 --- a/webui/configs/models_catalog.json +++ b/webui/configs/models_catalog.json @@ -6,14 +6,14 @@ "_comment": "Native WebUI catalog for model families enabled in registry.cpp. The embedded server loads one selected model or precision at a time and resolves paths relative to the configured models root. Missing packages appear as not installed; the Models page invokes the repository-level model_manager_v2.py through the server to install spec-backed GGUF packages in the background. 'task' must be one of: tts, asr, vad, diar, sep, gen, clon, vc, s2s, align, vdes, spk, svc. 'download_id' is a model_specs package id and is omitted for bundled assets such as silero_vad. Optional per-entry keys include input_hint, default_options, session_options, and min_vram_gb. min_vram_gb is an estimated minimum CUDA VRAM value used only for UI guidance.", "models": [ - { "id": "omnivoice", "display_name": "OmniVoice (tts)", "family": "omnivoice", "path": "models/OmniVoice", "task": "tts", "mode": "offline", "download_id": "omnivoice", "min_vram_gb": 10 }, - { "id": "pocket-tts", "display_name": "Pocket TTS (tts)", "family": "pocket_tts", "path": "models/pocket-tts", "task": "tts", "mode": "offline", "download_id": "pocket_tts", "min_vram_gb": 2 }, + { "id": "omnivoice", "display_name": "OmniVoice (tts)", "family": "omnivoice", "path": "models/OmniVoice-GGUF", "task": "tts", "mode": "offline", "download_id": "omnivoice_q8_0", "min_vram_gb": 10 }, + { "id": "pocket-tts", "display_name": "Pocket TTS (tts)", "family": "pocket_tts", "path": "models/PocketTTS-GGUF/english", "task": "tts", "mode": "offline", "download_id": "pocket_tts_english_q8_0", "min_vram_gb": 2 }, { "id": "dots-tts-soar", "display_name": "DotTTS SOAR (tts + clone)", "family": "dots_tts", "path": "models/DotTTS-SOAR-GGUF", "task": "tts", "mode": "offline", "download_id": "dots_tts_soar_q8_0", "min_vram_gb": 8 }, { "id": "dots-tts-meanflow", "display_name": "DotTTS MeanFlow (tts + clone)", "family": "dots_tts", "path": "models/DotTTS-MF-GGUF", "task": "tts", "mode": "offline", "download_id": "dots_tts_mf_q8_0", "min_vram_gb": 8 }, { "id": "neutts-2e", "display_name": "NeuTTS 2E (tts, preset voices)", "family": "neutts", "path": "models/NeuTTS-2E-GGUF", "task": "tts", "mode": "offline", "download_id": "neutts_2e_orig", "min_vram_gb": 4 }, - { "id": "qwen3-tts", "display_name": "Qwen3-TTS 0.6B (tts)", "family": "qwen3_tts", "path": "models/Qwen3-TTS-12Hz-0.6B-Base", "task": "tts", "mode": "offline", "download_id": "qwen3_tts_0_6b_base", "min_vram_gb": 5 }, - { "id": "qwen3-tts-1.7b", "display_name": "Qwen3-TTS 1.7B Base (tts)", "family": "qwen3_tts", "path": "models/Qwen3-TTS-12Hz-1.7B-Base", "task": "tts", "mode": "offline", "download_id": "qwen3_tts_1_7b_base", "min_vram_gb": 8 }, - { "id": "qwen3-tts-1.7b-custom", "display_name": "Qwen3-TTS 1.7B CustomVoice (tts)", "family": "qwen3_tts", "path": "models/Qwen3-TTS-12Hz-1.7B-CustomVoice", "task": "tts", "mode": "offline", "download_id": "qwen3_tts_1_7b_custom_voice", "min_vram_gb": 8 }, + { "id": "qwen3-tts", "display_name": "Qwen3-TTS 0.6B (tts)", "family": "qwen3_tts", "path": "models/Qwen3-TTS-12Hz-0.6B-Base-GGUF", "task": "tts", "mode": "offline", "download_id": "qwen3_tts_0_6b_base_q8_0", "min_vram_gb": 5 }, + { "id": "qwen3-tts-1.7b", "display_name": "Qwen3-TTS 1.7B Base (tts)", "family": "qwen3_tts", "path": "models/Qwen3-TTS-12Hz-1.7B-Base-GGUF", "task": "tts", "mode": "offline", "download_id": "qwen3_tts_1_7b_base_q8_0", "min_vram_gb": 8 }, + { "id": "qwen3-tts-1.7b-custom", "display_name": "Qwen3-TTS 1.7B CustomVoice (tts)", "family": "qwen3_tts", "path": "models/Qwen3-TTS-12Hz-1.7B-CustomVoice-GGUF", "task": "tts", "mode": "offline", "download_id": "qwen3_tts_1_7b_customvoice_q8_0", "min_vram_gb": 8 }, { "id": "breeze-tts", "display_name": "BreezeTTS 2 VoiceDesign", "family": "breeze_tts", "path": "models/Breeze-TTS-2-GGUF/breeze-tts-2-q8_0.gguf", "task": "vdes", "mode": "offline", "download_id": "breeze_tts_2_q8_0", "min_vram_gb": 8, "input_hint_en": "**BreezeTTS 2 VoiceDesign**: enter text and describe the target voice in Model parameters. No reference voice is required." }, { "id": "breeze-tts-clone", "display_name": "BreezeTTS 2 Clone", "family": "breeze_tts", "path": "models/Breeze-TTS-2-GGUF/breeze-tts-2-q8_0.gguf", "task": "clon", "mode": "offline", "download_id": "breeze_tts_2_q8_0", "min_vram_gb": 8, @@ -22,13 +22,13 @@ "input_hint_en": "**CosyVoice3 Clone**: upload a reference voice and provide the matching reference transcript. Use `template_name` for zero-shot or cross-lingual requests." }, { "id": "cosyvoice3-instruct", "display_name": "CosyVoice3 Instruct", "family": "cosyvoice3", "path": "models/CosyVoice3-GGUF/cosyvoice3-q8_0.gguf", "task": "tts", "mode": "offline", "download_id": "cosyvoice3_q8_0", "min_vram_gb": 8, "input_hint_en": "**CosyVoice3 Instruct**: upload a reference voice, provide its transcript, and set `template_name=instruct` with an instruction." }, - { "id": "miotts", "display_name": "MioTTS 1.7B (tts; needs MioCodec)", "family": "miotts", "path": "models/MioTTS-1.7B", "task": "tts", "mode": "offline", "download_id": "miotts_1_7b", "min_vram_gb": 8 }, + { "id": "miotts", "display_name": "MioTTS 1.7B (tts; needs MioCodec)", "family": "miotts", "path": "models/MioTTS-1.7B-GGUF", "task": "tts", "mode": "offline", "download_id": "miotts_1_7b_q8_0", "min_vram_gb": 8 }, { "id": "soprano-tts", "display_name": "Soprano TTS (tts)", "family": "soprano_tts", "path": "models/Soprano-1.1-80M-GGUF", "task": "tts", "mode": "offline", "download_id": "soprano_1_1_80m_q8_0", "min_vram_gb": 1 }, - { "id": "voxcpm2", "display_name": "VoxCPM2 (tts)", "family": "voxcpm2", "path": "models/VoxCPM2", "task": "tts", "mode": "offline", "download_id": "voxcpm2", "session_options": { "voxcpm2.weight_type": "q8_0" }, "min_vram_gb": 6 }, + { "id": "voxcpm2", "display_name": "VoxCPM2 (tts)", "family": "voxcpm2", "path": "models/VoxCPM2-GGUF", "task": "tts", "mode": "offline", "download_id": "voxcpm2_q8_0", "session_options": { "voxcpm2.weight_type": "q8_0" }, "min_vram_gb": 6 }, { "id": "voxcpm1", "display_name": "VoxCPM1 0.5B (tts + clone)", "family": "voxcpm1", "path": "models/VoxCPM1-GGUF", "task": "tts", "mode": "offline", "download_id": "voxcpm1_0_5b_q8_0", "min_vram_gb": 4 }, - { "id": "vibevoice", "display_name": "VibeVoice 1.5B/7B (tts, long-form/multi-speaker)", "family": "vibevoice", "path": "models/VibeVoice-1.5B", "task": "tts", "mode": "offline", "download_id": "vibevoice_1_5b", "min_vram_gb": 7 }, + { "id": "vibevoice", "display_name": "VibeVoice 1.5B/7B (tts, long-form/multi-speaker)", "family": "vibevoice", "path": "models/VibeVoice-1.5B-GGUF", "task": "tts", "mode": "offline", "download_id": "vibevoice_1_5b_q8_0", "min_vram_gb": 7 }, { "id": "vibevoice-7b", "display_name": "VibeVoice 7B (tts, long-form/multi-speaker)", "family": "vibevoice", "path": "models/VibeVoice-7B-GGUF", "task": "tts", "mode": "offline", "download_id": "vibevoice_7b_q8_0", "min_vram_gb": 16 }, - { "id": "index-tts2", "display_name": "IndexTTS2 (tts 中英克隆+情感)", "display_name_en": "IndexTTS2 (tts, zh/en clone + emotion)", "family": "index_tts2", "path": "models/IndexTTS-2", "task": "tts", "mode": "offline", "download_id": "index_tts2", "min_vram_gb": 8 }, + { "id": "index-tts2", "display_name": "IndexTTS2 (tts 中英克隆+情感)", "display_name_en": "IndexTTS2 (tts, zh/en clone + emotion)", "family": "index_tts2", "path": "models/IndexTTS2-GGUF", "task": "tts", "mode": "offline", "download_id": "index_tts2_q8_0", "min_vram_gb": 8 }, { "id": "index-tts2.5", "display_name": "IndexTTS2.5 (tts 多语种克隆+情感, GGUF Q8)", "display_name_en": "IndexTTS2.5 (tts, zh/en/ja/es/ar clone + emotion, GGUF Q8)", "family": "index_tts2", "path": "models/IndexTTS2.5-GGUF", "task": "tts", "mode": "offline", "download_id": "index_tts2_5_q8_0", "min_vram_gb": 8, "input_hint": "**IndexTTS2.5**：中/英/日/西/阿零样本克隆；上传参考音色即克隆；可在『其它参数(JSON)』里传 `lang`（默认 auto：含汉字按中文，否则按英文）与情感选项。许可证为 bilibili Model Use License（非 OSI），商用前请确认条款。", "input_hint_en": "**IndexTTS2.5**: zero-shot cloning in zh/en/ja/es/ar. Upload a reference voice to clone; pass `lang` (default auto: zh when the text contains Han characters, otherwise en) and emotion options through the JSON box. Weights are under the bilibili Model Use License (not OSI-approved) — check terms before commercial use." }, @@ -36,37 +36,37 @@ "input_hint": "**Irodori-TTS v4 Small**：日语 TTS；可不上传参考音色直接生成，也可上传参考音色进行克隆；可在声音设计页用日语 caption 描述音色。", "input_hint_en": "**Irodori-TTS v4 Small**: Japanese TTS. Generate without a reference voice, clone from an uploaded reference, or use the voice-design page with a Japanese voice caption." }, { "id": "irodori-tts-v3-500m", "display_name": "Irodori-TTS 500M v3 (tts 日语)", "display_name_en": "Irodori-TTS 500M v3 (ja tts)", "family": "irodori_tts", "path": "models/Irodori-TTS-500M-v3-GGUF", "task": "tts", "mode": "offline", "download_id": "irodori_tts_500m_v3_q8_0", "min_vram_gb": 4 }, - { "id": "moss-tts-local", "display_name": "MOSS-TTS-Local v1.5 (tts)", "family": "moss_tts_local", "path": "models/MOSS-TTS-Local-Transformer-v1.5", "task": "tts", "mode": "offline", "download_id": "moss_tts_local_v1_5", "min_vram_gb": 8 }, - { "id": "moss-tts-nano", "display_name": "MOSS-TTS-Nano 100M (tts)", "family": "moss_tts_nano", "path": "models/MOSS-TTS-Nano-100M", "task": "tts", "mode": "offline", "download_id": "moss_tts_nano_100m", "min_vram_gb": 2 }, + { "id": "moss-tts-local", "display_name": "MOSS-TTS-Local v1.5 (tts)", "family": "moss_tts_local", "path": "models/MOSS-TTS-Local-v1.5-GGUF", "task": "tts", "mode": "offline", "download_id": "moss_tts_local_v1_5_q8_0", "min_vram_gb": 8 }, + { "id": "moss-tts-nano", "display_name": "MOSS-TTS-Nano 100M (tts)", "family": "moss_tts_nano", "path": "models/MOSS-TTS-Nano-100M-GGUF", "task": "tts", "mode": "offline", "download_id": "moss_tts_nano_100m_q8_0", "min_vram_gb": 2 }, { "id": "magpie-tts", "display_name": "MagpieTTS Multilingual 357M v2607 (tts, preset voices)", "display_name_en": "MagpieTTS Multilingual 357M v2607 (tts, preset voices)", "family": "magpie_tts", "path": "models/MagpieTTS-Multilingual-357M-GGUF", "task": "tts", "mode": "offline", "download_id": "magpie_tts_q8_0", "min_vram_gb": 4, "input_hint": "**MagpieTTS**：多语种离线 TTS；使用打包 speaker map 里的 `voice_id`，不需要上传参考音频。当前 GGUF 包不包含日语 phoneme 表，因此日语路径不可用。", "input_hint_en": "**MagpieTTS**: multilingual offline TTS with packaged speaker prompts selected by `voice_id`; no reference upload is needed. The current GGUF package does not include the Japanese phoneme table, so Japanese is not available." }, - { "id": "fireredtts3-instruct", "display_name": "FireRedTTS3 Instruct Clone", "family": "fireredtts3", "path": "models/FireRedTTS3-Instruct-GGUF/fireredtts3-instruct-q8_0.gguf", "task": "clon", "mode": "offline", "download_id": "fireredtts3_instruct_q8_0", "min_vram_gb": 8, + { "id": "fireredtts3-instruct", "display_name": "FireRedTTS3 Instruct Clone", "family": "fireredtts3", "path": "models/FireRedTTS3-Instruct-GGUF", "task": "clon", "mode": "offline", "download_id": "fireredtts3_instruct_q8_0", "min_vram_gb": 8, "input_hint_en": "**FireRedTTS3 Instruct Clone**: official Instruct `generate_tts` path. Upload a reference voice and provide the matching reference transcript. For no-reference voice design, use the VoiceDesign entry." }, - { "id": "fireredtts3-base", "display_name": "FireRedTTS3 Base (voice clone)", "family": "fireredtts3", "path": "models/FireRedTTS3-Base-GGUF/fireredtts3-base-q8_0.gguf", "task": "clon", "mode": "offline", "download_id": "fireredtts3_base_q8_0", "min_vram_gb": 8, + { "id": "fireredtts3-base", "display_name": "FireRedTTS3 Base (voice clone)", "family": "fireredtts3", "path": "models/FireRedTTS3-Base-GGUF", "task": "clon", "mode": "offline", "download_id": "fireredtts3_base_q8_0", "min_vram_gb": 8, "input_hint_en": "**FireRedTTS3 Base**: zero-shot voice cloning. Upload a reference voice and provide the matching reference transcript." }, - { "id": "firered-audio-tts", "display_name": "FireRedAudio Clone", "family": "firered_audio", "path": "models/FireRedAudio-GGUF/firered-audio-q8_0.gguf", "task": "clon", "mode": "offline", "download_id": "firered_audio_q8_0", "min_vram_gb": 10, + { "id": "firered-audio-tts", "display_name": "FireRedAudio Clone", "family": "firered_audio", "path": "models/FireRedAudio-GGUF", "task": "clon", "mode": "offline", "download_id": "firered_audio_q8_0", "min_vram_gb": 10, "input_hint_en": "**FireRedAudio Clone**: upload a reference voice and provide the matching reference transcript. For no-reference voice design, use the VoiceDesign entry." }, - { "id": "supertonic", "display_name": "Supertonic 3 (tts 预置音色/多语种)", "display_name_en": "Supertonic 3 (tts, preset voices)", "family": "supertonic", "path": "models/supertonic-3", "task": "tts", "mode": "offline", "download_id": "supertonic_3", "min_vram_gb": 2 }, - { "id": "higgs-audio-tts", "display_name": "Higgs Audio v3 TTS 4B (tts 克隆, GGUF Q8)", "display_name_en": "Higgs Audio v3 TTS 4B (tts + clone, GGUF Q8)", "family": "higgs_audio_tts", "path": "models/Higgs-Audio-v3-TTS-4B-GGUF", "task": "tts", "mode": "offline", "download_id": "higgs_audio_v3_tts_4b", "min_vram_gb": 6, + { "id": "supertonic", "display_name": "Supertonic 3 (tts 预置音色/多语种)", "display_name_en": "Supertonic 3 (tts, preset voices)", "family": "supertonic", "path": "models/Supertonic-3-GGUF", "task": "tts", "mode": "offline", "download_id": "supertonic_3_orig", "min_vram_gb": 2 }, + { "id": "higgs-audio-tts", "display_name": "Higgs Audio v3 TTS 4B (tts 克隆, GGUF Q8)", "display_name_en": "Higgs Audio v3 TTS 4B (tts + clone, GGUF Q8)", "family": "higgs_audio_tts", "path": "models/Higgs-Audio-v3-TTS-4B-GGUF", "task": "tts", "mode": "offline", "download_id": "higgs_audio_tts_4b_q8_0", "min_vram_gb": 6, "input_hint": "**Higgs Audio v3 TTS**：Q8_0 GGUF 包（权重已量化，不用再设 weight_type）；上传参考音色即声音克隆，留空用默认音色；长文本自动分段。", "input_hint_en": "**Higgs Audio v3 TTS**: Q8_0 GGUF package (already quantized — no weight_type needed). Upload a reference voice to clone, or leave it empty for the default voice; long text is chunked automatically." }, - { "id": "fish-audio-s2-pro", "display_name": "Fish Audio S2 Pro (tts 克隆/控制标记, GGUF Q8)", "display_name_en": "Fish Audio S2 Pro (tts + clone/control tags, GGUF Q8)", "family": "fish_audio", "path": "models/Fish-Audio-S2-Pro-GGUF", "task": "tts", "mode": "offline", "download_id": "fish_audio_s2_pro", "min_vram_gb": 8, + { "id": "fish-audio-s2-pro", "display_name": "Fish Audio S2 Pro (tts 克隆/控制标记, GGUF Q8)", "display_name_en": "Fish Audio S2 Pro (tts + clone/control tags, GGUF Q8)", "family": "fish_audio", "path": "models/Fish-Audio-S2-Pro-GGUF", "task": "tts", "mode": "offline", "download_id": "fish_audio_s2_pro_q8_0", "min_vram_gb": 8, "input_hint": "**Fish Audio S2 Pro**：Q8_0 GGUF 包；中英+自动语种；上传参考音色即克隆；正文里可写行内控制标记（如 (laugh)）。", "input_hint_en": "**Fish Audio S2 Pro**: Q8_0 GGUF package; English/Chinese plus auto language. Upload a reference voice to clone; inline control tags such as (laugh) can be written in the text." }, { "id": "audio8-tts", "display_name": "Audio8 TTS Preview 0.6B (tts 克隆, GGUF Q8)", "display_name_en": "Audio8 TTS Preview 0.6B (tts + clone, GGUF Q8)", "family": "audio8_tts", "path": "models/Audio8-TTS-Preview-0.6B-GGUF", "task": "tts", "mode": "offline", "download_id": "audio8_tts_preview_0_6b_q8_0", "min_vram_gb": 4, "input_hint": "**Audio8 TTS Preview 0.6B**：多语种 TTS / 零样本克隆（支持 yue/zh/nl/en/fr/de/it/ja/ko/pl/es/auto）；上传参考音色+参考文本即克隆，留空为普通 TTS；长文本自动分句。", "input_hint_en": "**Audio8 TTS Preview 0.6B**: multilingual TTS and zero-shot clone (yue/zh/nl/en/fr/de/it/ja/ko/pl/es/auto). Upload a reference voice + transcript to clone; leave empty for plain TTS. Long text is chunked automatically." }, - { "id": "glm-tts", "display_name": "GLM-TTS (tts 克隆, 社区)", "display_name_en": "GLM-TTS (tts + clone, community)", "family": "glm_tts", "path": "models/GLM-TTS", "task": "tts", "mode": "offline", "download_id": "glm_tts", "min_vram_gb": 8, + { "id": "glm-tts", "display_name": "GLM-TTS (tts 克隆, 社区)", "display_name_en": "GLM-TTS (tts + clone, community)", "family": "glm_tts", "path": "models/GLM-TTS-Q8", "task": "tts", "mode": "offline", "download_id": "glm_tts_q8_0", "min_vram_gb": 8, "input_hint": "**GLM-TTS**（社区模型）：中英 TTS / voice clone；上传参考音色即克隆。", "input_hint_en": "**GLM-TTS** (community): Chinese/English TTS and voice clone. Upload a reference voice to clone." }, - { "id": "outetts", "display_name": "Llama-OuteTTS 1.0 1B (tts 克隆, 社区)", "display_name_en": "Llama-OuteTTS 1.0 1B (tts + clone, community)", "family": "outetts", "path": "models/Llama-OuteTTS-1.0-1B", "task": "tts", "mode": "offline", "download_id": "outetts_1_0_1b", "min_vram_gb": 4, + { "id": "outetts", "display_name": "Llama-OuteTTS 1.0 1B (tts 克隆, 社区)", "display_name_en": "Llama-OuteTTS 1.0 1B (tts + clone, community)", "family": "outetts", "path": "models/Llama-OuteTTS-1.0-1B_Q8", "task": "tts", "mode": "offline", "download_id": "outetts_1_0_1b_q8_0", "min_vram_gb": 4, "input_hint": "**OuteTTS 1.0 1B**（社区模型）：23 种语言，DAC 编解码；上传参考音色即克隆。", "input_hint_en": "**OuteTTS 1.0 1B** (community): 23 languages, IBM DAC codec. Upload a reference voice to clone." }, - { "id": "vietneu-tts", "display_name": "VieNeu-TTS v3 Turbo (tts 越南语, 社区)", "display_name_en": "VieNeu-TTS v3 Turbo (vi tts, community)", "family": "vietneu_tts", "path": "models/VieNeu-TTS-v3-Turbo", "task": "tts", "mode": "offline", "download_id": "vietneu_tts_v3_turbo", "min_vram_gb": 4, + { "id": "vietneu-tts", "display_name": "VieNeu-TTS v3 Turbo (tts 越南语, 社区)", "display_name_en": "VieNeu-TTS v3 Turbo (vi tts, community)", "family": "vietneu_tts", "path": "models/VieNeu-TTS-v3-Turbo-GGUF", "task": "tts", "mode": "offline", "download_id": "vietneu_tts_v3_turbo_q8_0", "min_vram_gb": 4, "input_hint": "**VieNeu-TTS v3 Turbo**（社区模型）：越南语 / 英语；上传参考音色即克隆。", "input_hint_en": "**VieNeu-TTS v3 Turbo** (community): Vietnamese and English. Upload a reference voice to clone." }, - { "id": "inflect-v2", "display_name": "Inflect Micro v2 (tts 英语, 社区)", "display_name_en": "Inflect Micro v2 (en tts, community)", "family": "inflect_v2", "path": "models/Inflect-Micro-v2", "task": "tts", "mode": "offline", "download_id": "inflect_micro_v2", "min_vram_gb": 2, + { "id": "inflect-v2", "display_name": "Inflect Micro v2 (tts 英语, 社区)", "display_name_en": "Inflect Micro v2 (en tts, community)", "family": "inflect_v2", "path": "models/Inflect-Micro-v2-GGUF", "task": "tts", "mode": "offline", "download_id": "inflect_micro_v2_orig", "min_vram_gb": 2, "input_hint": "**Inflect Micro v2**（社区模型）：英语离线 TTS；Micro 是默认包，Nano 可通过模型管理器另装后手动选择路径。", "input_hint_en": "**Inflect Micro v2** (community): English offline TTS. Micro is the default package; Nano can be installed separately and selected manually." }, { "id": "dramabox", "display_name": "DramaBox (tts 克隆, GGUF Q8)", "display_name_en": "DramaBox (tts + clone, GGUF Q8)", "family": "dramabox", "path": "models/DramaBox-GGUF", "task": "tts", "mode": "offline", "download_id": "dramabox_q8_0", "min_vram_gb": 16, @@ -79,100 +79,100 @@ { "id": "echo-tts", "display_name": "Echo-TTS (voice clone)", "family": "echo_tts", "path": "models/Echo-TTS-GGUF", "task": "clon", "mode": "offline", "download_id": "echo_tts_q8_0", "min_vram_gb": 8, "input_hint_en": "**Echo-TTS**: English zero-shot cloning at 44.1 kHz. Upload a reference voice -- no transcript needed. Output is CC-BY-NC-SA and may not be used commercially." }, - { "id": "chatterbox", "display_name": "Chatterbox (voice clone)", "family": "chatterbox", "path": "models/chatterbox", "task": "clon", "mode": "offline", "download_id": "chatterbox", "min_vram_gb": 12 }, + { "id": "chatterbox", "display_name": "Chatterbox (voice clone)", "family": "chatterbox", "path": "models/Chatterbox-GGUF", "task": "clon", "mode": "offline", "download_id": "chatterbox_q8_0", "min_vram_gb": 12 }, { "id": "chatterbox-turbo", "display_name": "Chatterbox Turbo (tts)", "family": "chatterbox_turbo", "path": "models/Chatterbox-Turbo-GGUF/chatterbox-turbo-q8_0.gguf", "task": "tts", "mode": "offline", "download_id": "chatterbox_turbo_q8_0", "min_vram_gb": 4, "input_hint_en": "**Chatterbox Turbo**: fast English TTS with the built-in voice. No reference voice is required." }, - { "id": "ace-step", "display_name": "ACE-Step 1.5 (music gen)", "family": "ace_step", "path": "models/Ace-Step1.5", "task": "gen", "mode": "offline", "download_id": "ace_step", "session_options": { "ace_step.mem_saver": "true", "ace_step.dit_weight_type": "q8_0", "ace_step.text_encoder_weight_type": "q8_0", "ace_step.planner_weight_type": "q8_0" }, "min_vram_gb": 8 }, + { "id": "ace-step", "display_name": "ACE-Step 1.5 (music gen)", "family": "ace_step", "path": "models/ACE-Step1.5-GGUF", "task": "gen", "mode": "offline", "download_id": "ace_step_turbo_bf16", "session_options": { "ace_step.mem_saver": "true", "ace_step.dit_weight_type": "q8_0", "ace_step.text_encoder_weight_type": "q8_0", "ace_step.planner_weight_type": "q8_0" }, "min_vram_gb": 8 }, { "id": "minimax-music3", "display_name": "MiniMax-Music3 (song gen)", "family": "minimax_music3", "path": "models/MiniMax-Music3-GGUF", "task": "gen", "mode": "offline", "download_id": "minimax_music3_q4_0", "min_vram_gb": 12 }, - { "id": "stable-audio-small-music","display_name": "Stable Audio 3 Small Music (gen)", "family": "stable_audio", "path": "models/stable-audio-3-small-music", "task": "gen", "mode": "offline", "download_id": "stable_audio_3_small_music", "min_vram_gb": 4 }, - { "id": "stable-audio-small-sfx", "display_name": "Stable Audio 3 Small SFX (gen)", "family": "stable_audio", "path": "models/stable-audio-3-small-sfx", "task": "gen", "mode": "offline", "download_id": "stable_audio_3_small_sfx", "min_vram_gb": 4 }, - { "id": "stable-audio-medium", "display_name": "Stable Audio 3 Medium (gen)", "family": "stable_audio", "path": "models/stable-audio-3-medium", "task": "gen", "mode": "offline", "download_id": "stable_audio_3_medium", "session_options": { "stable_audio.mem_saver": "true" }, "min_vram_gb": 10 }, - { "id": "heartmula", "display_name": "HeartMuLa 3B (music gen)", "family": "heartmula", "path": "models/HeartMuLa", "task": "gen", "mode": "offline", "download_id": "heartmula", "session_options": { "heartmula.mem_saver": "true" }, "min_vram_gb": 24 }, - { "id": "minimax-h3", "display_name": "MiniMax-H3 Q4 (sound generation)", "family": "minimax_h3", "path": "models/MiniMax-H3-Q4-GGUF/dit.gguf", "task": "gen", "mode": "offline", "download_id": "minimax_h3", "min_vram_gb": 20, + { "id": "stable-audio-small-music","display_name": "Stable Audio 3 Small Music (gen)", "family": "stable_audio", "path": "models/Stable-Audio-3-Small-Music-GGUF", "task": "gen", "mode": "offline", "download_id": "stable_audio_3_small_music_q8_0", "min_vram_gb": 4 }, + { "id": "stable-audio-small-sfx", "display_name": "Stable Audio 3 Small SFX (gen)", "family": "stable_audio", "path": "models/Stable-Audio-3-Small-SFX-GGUF", "task": "gen", "mode": "offline", "download_id": "stable_audio_3_small_sfx_q8_0", "min_vram_gb": 4 }, + { "id": "stable-audio-medium", "display_name": "Stable Audio 3 Medium (gen)", "family": "stable_audio", "path": "models/Stable-Audio-3-Medium-GGUF", "task": "gen", "mode": "offline", "download_id": "stable_audio_3_medium_q8_0", "session_options": { "stable_audio.mem_saver": "true" }, "min_vram_gb": 10 }, + { "id": "heartmula", "display_name": "HeartMuLa 3B (music gen)", "family": "heartmula", "path": "models/HeartMuLa-GGUF", "task": "gen", "mode": "offline", "download_id": "heartmula_q8_0", "session_options": { "heartmula.mem_saver": "true" }, "min_vram_gb": 24 }, + { "id": "minimax-h3", "display_name": "MiniMax-H3 Q4 (sound generation)", "family": "minimax_h3", "path": "models/MiniMax-H3-Q4-GGUF", "task": "gen", "mode": "offline", "download_id": "minimax_h3_q4_k", "min_vram_gb": 20, "default_options": { "num_inference_steps": 12, "height": 32, "width": 32, "num_frames": 241, "guidance_scale": 1.0, "dit_acceleration": "none", "return_video": false }, "input_hint_en": "MiniMax-H3 uses a joint audio/video DiT. The default Q4 DiT is the quality-first choice; the optional CUDA-only INT8 ConvRot DiT trades slightly more VRAM for higher speed. Native Studio uses 12 denoising steps, a 32x32 latent canvas, quality-first full-DiT execution, and disables video decoding for practical audio-only generation on a 24 GB GPU." }, - { "id": "midashenglm-gen", "display_name": "MiDashengLM-Gen (audio generation)", "family": "midashenglm_gen", "path": "models/MiDashengLM-Gen-GGUF/midashenglm-gen-q8_0.gguf", "task": "gen", "mode": "offline", "download_id": "midashenglm_gen_q8_0", "min_vram_gb": 8, + { "id": "midashenglm-gen", "display_name": "MiDashengLM-Gen (audio generation)", "family": "midashenglm_gen", "path": "models/MiDashengLM-Gen-GGUF", "task": "gen", "mode": "offline", "download_id": "midashenglm_gen_q8_0", "min_vram_gb": 8, "input_hint_en": "**MiDashengLM-Gen**: text-conditioned audio generation. The duration field controls the generation budget." }, - { "id": "controlfoley", "display_name": "ControlFoley (Foley/SFX)", "family": "controlfoley", "path": "models/ControlFoley-GGUF/controlfoley-large-44k-q8_0.gguf", "task": "gen", "mode": "offline", "download_id": "controlfoley_large_44k_q8_0", "min_vram_gb": 12, + { "id": "controlfoley", "display_name": "ControlFoley (Foley/SFX)", "family": "controlfoley", "path": "models/ControlFoley-GGUF", "task": "gen", "mode": "offline", "download_id": "controlfoley_large_44k_q8_0", "min_vram_gb": 12, "request_options": ["video"], "input_hint_en": "**ControlFoley**: Foley generation from text, video, text+video, audio+video, or video only. Upload video in the Video field; upload source audio for AC-V2A." }, - { "id": "firered-audio-semantic-edit", "display_name": "FireRedAudio Semantic Edit", "family": "firered_audio", "path": "models/FireRedAudio-GGUF/firered-audio-q8_0.gguf", "task": "gen", "mode": "offline", "download_id": "firered_audio_q8_0", "min_vram_gb": 10, + { "id": "firered-audio-semantic-edit", "display_name": "FireRedAudio Semantic Edit", "family": "firered_audio", "path": "models/FireRedAudio-GGUF", "task": "gen", "mode": "offline", "download_id": "firered_audio_q8_0", "min_vram_gb": 10, "input_hint_en": "**FireRedAudio Semantic Edit**: upload source audio and describe the content edit in Model parameters." }, - { "id": "firered-audio-acoustic-edit", "display_name": "FireRedAudio Acoustic Edit", "family": "firered_audio", "path": "models/FireRedAudio-GGUF/firered-audio-q8_0.gguf", "task": "gen", "mode": "offline", "download_id": "firered_audio_q8_0", "min_vram_gb": 10, + { "id": "firered-audio-acoustic-edit", "display_name": "FireRedAudio Acoustic Edit", "family": "firered_audio", "path": "models/FireRedAudio-GGUF", "task": "gen", "mode": "offline", "download_id": "firered_audio_q8_0", "min_vram_gb": 10, "input_hint_en": "**FireRedAudio Acoustic Edit**: upload source audio and use a trained acoustic instruction such as `shift the pitch by 3 steps`." }, - { "id": "qwen3-asr", "display_name": "Qwen3-ASR 0.6B (asr)", "family": "qwen3_asr", "path": "models/Qwen3-ASR-0.6B", "task": "asr", "mode": "offline", "download_id": "qwen3_asr_0_6b", "min_vram_gb": 3 }, - { "id": "qwen3-asr-1.7b", "display_name": "Qwen3-ASR 1.7B HF (asr)", "family": "qwen3_asr", "path": "models/Qwen3-ASR-1.7B-hf", "task": "asr", "mode": "offline", "download_id": "qwen3_asr_1_7b_hf", "min_vram_gb": 6, + { "id": "qwen3-asr", "display_name": "Qwen3-ASR 0.6B (asr)", "family": "qwen3_asr", "path": "models/Qwen3-ASR-0.6B-GGUF", "task": "asr", "mode": "offline", "download_id": "qwen3_asr_0_6b_q8_0", "min_vram_gb": 3 }, + { "id": "qwen3-asr-1.7b", "display_name": "Qwen3-ASR 1.7B HF (asr)", "family": "qwen3_asr", "path": "models/Qwen3-ASR-1.7B-GGUF", "task": "asr", "mode": "offline", "download_id": "qwen3_asr_1_7b_q8_0", "min_vram_gb": 6, "input_hint": "**Qwen3-ASR 1.7B**（HF 原生权重，免转换）：精度高于 0.6B；长音频自动分段转写；8G 卡显存偏紧，长音频建议先短段试跑。", "input_hint_en": "**Qwen3-ASR 1.7B**: native Hugging Face weights with no conversion required. It is more accurate than the 0.6B model and automatically chunks long audio; test short clips first on an 8 GB GPU." }, - { "id": "citrinet-asr", "display_name": "Citrinet ASR (asr)", "family": "citrinet_asr", "path": "models/citrinet", "task": "asr", "mode": "offline", "download_id": "citrinet_asr", "min_vram_gb": 2 }, - { "id": "nemotron-asr", "display_name": "Nemotron 3.5 ASR 0.6B (asr, 100+语种)", "display_name_en": "Nemotron 3.5 ASR 0.6B (asr, 100+ languages)", "family": "nemotron_asr", "path": "models/nemotron-3.5-asr-streaming-0.6b", "task": "asr", "mode": "offline", "download_id": "nemotron_asr", "min_vram_gb": 4, + { "id": "citrinet-asr", "display_name": "Citrinet ASR (asr)", "family": "citrinet_asr", "path": "models/Citrinet-ASR-GGUF", "task": "asr", "mode": "offline", "download_id": "citrinet_asr_q8_0", "min_vram_gb": 2 }, + { "id": "nemotron-asr", "display_name": "Nemotron 3.5 ASR 0.6B (asr, 100+语种)", "display_name_en": "Nemotron 3.5 ASR 0.6B (asr, 100+ languages)", "family": "nemotron_asr", "path": "models/Nemotron-3.5-ASR-Streaming-0.6B-GGUF", "task": "asr", "mode": "offline", "download_id": "nemotron_asr_q8_0", "min_vram_gb": 4, "input_hint": "**Nemotron ASR**：100+ 语种，语种码为 BCP-47（如 en-US / zh-CN），留空=auto；模型自带长音频处理。", "input_hint_en": "**Nemotron ASR**: supports more than 100 languages using BCP-47 codes such as en-US or zh-CN. Leave language blank for automatic detection; long audio is handled by the model." }, - { "id": "higgs-audio-stt", "display_name": "Higgs Audio v3 STT (asr, 英语)", "display_name_en": "Higgs Audio v3 STT (asr, English)", "family": "higgs_audio_stt", "path": "models/higgs-audio-v3-stt", "task": "asr", "mode": "offline", "download_id": "higgs_audio_stt", "min_vram_gb": 8, + { "id": "higgs-audio-stt", "display_name": "Higgs Audio v3 STT (asr, 英语)", "display_name_en": "Higgs Audio v3 STT (asr, English)", "family": "higgs_audio_stt", "path": "models/Higgs-Audio-v3-STT-GGUF", "task": "asr", "mode": "offline", "download_id": "higgs_audio_stt_q8_0", "min_vram_gb": 8, "input_hint": "**Higgs Audio STT**：英语转写；可在文本框填指令（默认相当于 Transcribe the speech.）；离线模式自动切分长音频。", "input_hint_en": "**Higgs Audio STT**: English transcription. The text box accepts an instruction; offline mode automatically chunks long audio." }, - { "id": "hviske-asr", "display_name": "Hviske v5.3 (asr, 丹麦语)", "display_name_en": "Hviske v5.3 (asr, Danish)", "family": "hviske_asr", "path": "models/hviske-v5.3", "task": "asr", "mode": "offline", "download_id": "hviske_asr", "min_vram_gb": 6, + { "id": "hviske-asr", "display_name": "Hviske v5.3 (asr, 丹麦语)", "display_name_en": "Hviske v5.3 (asr, Danish)", "family": "hviske_asr", "path": "models/Hviske-v5.3-GGUF", "task": "asr", "mode": "offline", "download_id": "hviske_asr_q8_0", "min_vram_gb": 6, "input_hint": "**Hviske ASR**：丹麦语专用；模型侧自动分段。", "input_hint_en": "**Hviske ASR**: dedicated Danish transcription with automatic model-side segmentation." }, - { "id": "vibevoice-asr", "display_name": "VibeVoice ASR (asr, 多语种+说话人分段)", "display_name_en": "VibeVoice ASR (asr, multilingual + speaker turns)", "family": "vibevoice_asr", "path": "models/VibeVoice-ASR", "task": "asr", "mode": "offline", "download_id": "vibevoice_asr", "min_vram_gb": 20, + { "id": "vibevoice-asr", "display_name": "VibeVoice ASR (asr, 多语种+说话人分段)", "display_name_en": "VibeVoice ASR (asr, multilingual + speaker turns)", "family": "vibevoice_asr", "path": "models/VibeVoice-ASR-GGUF", "task": "asr", "mode": "offline", "download_id": "vibevoice_asr_q8_0", "min_vram_gb": 20, "input_hint": "**VibeVoice ASR**：自动语种，可输出分段/说话人轮次；文本框可填上下文提示（如 The recording is a meeting conversation.）。权重 17.3G，8G 卡跑不动。", "input_hint_en": "**VibeVoice ASR**: automatic language detection with segment and speaker-turn output. The text box accepts a context prompt. Its 17.3 GB weights require substantially more than 8 GB VRAM." }, - { "id": "voxtral-realtime", "display_name": "Voxtral Mini 4B Realtime (asr, 自动语种+流式)", "display_name_en": "Voxtral Mini 4B Realtime (asr, auto + streaming)", "family": "voxtral_realtime", "path": "models/Voxtral-Mini-4B-Realtime-2602-GGUF", "task": "asr", "mode": "offline", "download_id": "voxtral_realtime", "min_vram_gb": 8 }, + { "id": "voxtral-realtime", "display_name": "Voxtral Mini 4B Realtime (asr, 自动语种+流式)", "display_name_en": "Voxtral Mini 4B Realtime (asr, auto + streaming)", "family": "voxtral_realtime", "path": "models/Voxtral-Mini-4B-Realtime-2602-GGUF", "task": "asr", "mode": "offline", "download_id": "voxtral_realtime_q8_0", "min_vram_gb": 8 }, { "id": "fun-asr-nano", "display_name": "Fun-ASR-Nano 2512 (asr, GGUF Q8)", "display_name_en": "Fun-ASR-Nano 2512 (asr, GGUF Q8)", "family": "fun_asr_nano", "path": "models/Fun-ASR-Nano-2512-GGUF", "task": "asr", "mode": "offline", "download_id": "fun_asr_nano_2512_q8_0", "min_vram_gb": 4, "input_hint": "**Fun-ASR-Nano**：轻量离线 ASR；支持 auto/中文/英语/日语。", "input_hint_en": "**Fun-ASR-Nano**: lightweight offline ASR; supports auto, Chinese, English and Japanese." }, - { "id": "parakeet-tdt", "display_name": "Parakeet-TDT 0.6B v3 (asr, 流式)", "display_name_en": "Parakeet-TDT 0.6B v3 (asr + streaming)", "family": "parakeet_tdt", "path": "models/parakeet-tdt-0.6b-v3", "task": "asr", "mode": "offline", "download_id": "parakeet_tdt", "min_vram_gb": 4, + { "id": "parakeet-tdt", "display_name": "Parakeet-TDT 0.6B v3 (asr, 流式)", "display_name_en": "Parakeet-TDT 0.6B v3 (asr + streaming)", "family": "parakeet_tdt", "path": "models/Parakeet-TDT-0.6B-v3-GGUF", "task": "asr", "mode": "offline", "download_id": "parakeet_tdt_q8_0", "min_vram_gb": 4, "input_hint": "**Parakeet-TDT**：离线/长音频/流式 ASR；支持多种欧洲语言，留空=自动。", "input_hint_en": "**Parakeet-TDT**: offline, long-form and streaming ASR for many European languages; leave language empty for auto." }, { "id": "kroko-asr", "display_name": "Kroko Community ASR (asr, GGUF Q8)", "display_name_en": "Kroko Community ASR (asr, GGUF Q8)", "family": "kroko_asr", "path": "models/Kroko-ASR-GGUF", "task": "asr", "mode": "offline", "download_id": "kroko_asr_community_q8_0", "min_vram_gb": 4, "input_hint": "**Kroko Community ASR**：GGUF Q8 包；离线转写，支持时间戳。", "input_hint_en": "**Kroko Community ASR**: GGUF Q8 package for offline transcription with timestamps." }, - { "id": "granite5asr", "display_name": "Granite Speech 5.0 470M TurboCTC (asr)", "display_name_en": "Granite Speech 5.0 470M TurboCTC (asr)", "family": "granite5asr", "path": "granite5asr", "task": "asr", "mode": "offline", "download_id": "granite5asr_q8_0", "min_vram_gb": 4, + { "id": "granite5asr", "display_name": "Granite Speech 5.0 470M TurboCTC (asr)", "display_name_en": "Granite Speech 5.0 470M TurboCTC (asr)", "family": "granite5asr", "path": "models/Granite-Speech-5.0-470M-TurboCTC-GGUF", "task": "asr", "mode": "offline", "download_id": "granite5asr_q8_0", "min_vram_gb": 4, "input_hint": "**Granite Speech 5.0 TurboCTC**：IBM 470M 英语 ASR；超快 Conformer CTC 转写；支持长音频自动分段与流式模式。", "input_hint_en": "**Granite Speech 5.0 TurboCTC**: IBM 470M English ASR with ultra-fast Conformer CTC architecture, supporting long-form audio segmentation and streaming mode." }, { "id": "sense-asr", "display_name": "SenseVoice-Small (asr, 流式, 社区)", "display_name_en": "SenseVoice-Small (asr + streaming, community)", "family": "sense_asr", "path": "models/SenseVoice-Small-GGUF", "task": "asr", "mode": "offline", "download_id": "sensevoice_small_q8", "min_vram_gb": 4, "input_hint": "**SenseVoice-Small**（社区模型）：多语种 ASR，事件/情感/语言标签，ITN 可开关；离线与流式模式。", "input_hint_en": "**SenseVoice-Small** (community): multilingual ASR with event/emotion/language tags, optional ITN; offline and streaming modes." }, - { "id": "firered-audio-asr", "display_name": "FireRedAudio (ASR / audio QA)", "family": "firered_audio", "path": "models/FireRedAudio-GGUF/firered-audio-q8_0.gguf", "task": "asr", "mode": "offline", "download_id": "firered_audio_q8_0", "min_vram_gb": 10, + { "id": "firered-audio-asr", "display_name": "FireRedAudio (ASR / audio QA)", "family": "firered_audio", "path": "models/FireRedAudio-GGUF", "task": "asr", "mode": "offline", "download_id": "firered_audio_q8_0", "min_vram_gb": 10, "input_hint_en": "**FireRedAudio ASR**: upload audio, then use the text box as the transcription or audio-understanding instruction." }, - { "id": "chatterbox-vc", "display_name": "Chatterbox (vc 声音转换)", "display_name_en": "Chatterbox (voice conversion)", "family": "chatterbox", "path": "models/chatterbox", "task": "vc", "mode": "offline", "download_id": "chatterbox", "min_vram_gb": 12, + { "id": "chatterbox-vc", "display_name": "Chatterbox (vc 声音转换)", "display_name_en": "Chatterbox (voice conversion)", "family": "chatterbox", "path": "models/Chatterbox-GGUF", "task": "vc", "mode": "offline", "download_id": "chatterbox_q8_0", "min_vram_gb": 12, "input_hint": "**Chatterbox VC**：上传源语音和目标音色参考；模型保留源语音内容，将说话人音色转换为目标音色，输出 24kHz 单声道。", "input_hint_en": "**Chatterbox VC**: upload source speech and a target-voice reference. It preserves the source content and converts the speaker identity; output is 24 kHz mono." }, - { "id": "meanvc2", "display_name": "MeanVC2 (voice conversion)", "display_name_en": "MeanVC2 (voice conversion)", "family": "meanvc2", "path": "models/MeanVC2-GGUF/meanvc2-120ms-40ms-fp32.gguf", "task": "vc", "mode": "offline", "download_id": "meanvc2_120ms_40ms_f32", "min_vram_gb": 6, + { "id": "meanvc2", "display_name": "MeanVC2 (voice conversion)", "display_name_en": "MeanVC2 (voice conversion)", "family": "meanvc2", "path": "models/MeanVC2-GGUF", "task": "vc", "mode": "offline", "download_id": "meanvc2_120ms_40ms_f32", "min_vram_gb": 6, "input_hint": "**MeanVC2**：上传源语音和目标音色参考；默认 120 ms / 40 ms checkpoint 使用 F32 GGUF。", "input_hint_en": "**MeanVC2**: upload source speech and a target-voice reference. The default 120 ms / 40 ms checkpoint uses F32 GGUF." }, - { "id": "vevo2", "display_name": "Vevo2 (vc 语音转换, GGUF Q8)", "display_name_en": "Vevo2 (voice conversion, GGUF Q8)", "family": "vevo2", "path": "models/Vevo2-GGUF", "task": "vc", "mode": "offline", "download_id": "vevo2_gguf", "min_vram_gb": 6 }, - { "id": "vevo2-svc", "display_name": "Vevo2 (svc 歌声转换, GGUF Q8)", "display_name_en": "Vevo2 (singing voice conversion, GGUF Q8)", "family": "vevo2", "path": "models/Vevo2-GGUF", "task": "svc", "mode": "offline", "download_id": "vevo2_gguf", "min_vram_gb": 6, + { "id": "vevo2", "display_name": "Vevo2 (vc 语音转换, GGUF Q8)", "display_name_en": "Vevo2 (voice conversion, GGUF Q8)", "family": "vevo2", "path": "models/Vevo2-GGUF", "task": "vc", "mode": "offline", "download_id": "vevo2_q8_0", "min_vram_gb": 6 }, + { "id": "vevo2-svc", "display_name": "Vevo2 (svc 歌声转换, GGUF Q8)", "display_name_en": "Vevo2 (singing voice conversion, GGUF Q8)", "family": "vevo2", "path": "models/Vevo2-GGUF", "task": "svc", "mode": "offline", "download_id": "vevo2_q8_0", "min_vram_gb": 6, "input_hint": "**Vevo2 歌声转换 (svc)**：上传源歌声 + 目标歌手参考音色，默认 route=style_preserved_svc。style_converted_svc / singing_style_conversion 等风格转换 route 需在『其它参数(JSON)』里补 `style_ref`（服务器本地 wav 路径）/ `style_ref_text` / `target_text`。", "input_hint_en": "**Vevo2 singing conversion**: upload source singing and a target-singer reference. The default route is style_preserved_svc; style-conversion routes also accept style_ref, style_ref_text and target_text in Additional options." }, - { "id": "vevo2-s2s", "display_name": "Vevo2 (s2s 语音编辑, GGUF Q8)", "display_name_en": "Vevo2 (speech editing, GGUF Q8)", "family": "vevo2", "path": "models/Vevo2-GGUF", "task": "s2s", "mode": "offline", "download_id": "vevo2_gguf", "min_vram_gb": 6, + { "id": "vevo2-s2s", "display_name": "Vevo2 (s2s 语音编辑, GGUF Q8)", "display_name_en": "Vevo2 (speech editing, GGUF Q8)", "family": "vevo2", "path": "models/Vevo2-GGUF", "task": "s2s", "mode": "offline", "download_id": "vevo2_q8_0", "min_vram_gb": 6, "input_hint": "**Vevo2 语音编辑 (s2s)**：上传要编辑的源语音，并在『其它参数(JSON)』里填 `{\"target_text\": \"替换后的完整句子\"}`（编辑保持原说话人音色，可不上传目标音色）。", "input_hint_en": "**Vevo2 speech editing**: upload source speech and set target_text to the complete replacement sentence in Additional options. Editing preserves the original speaker and does not require a target-voice reference." }, - { "id": "seed-vc", "display_name": "Seed-VC (vc 语音转换)", "display_name_en": "Seed-VC (voice conversion)", "family": "seed_vc", "path": "models/SeedVC-MLX", "task": "vc", "mode": "offline", "download_id": "seed_vc", "min_vram_gb": 4 }, - { "id": "seed-vc-svc", "display_name": "Seed-VC (svc 歌声转换)", "display_name_en": "Seed-VC (singing voice conversion)", "family": "seed_vc", "path": "models/SeedVC-MLX", "task": "svc", "mode": "offline", "download_id": "seed_vc", "min_vram_gb": 4, + { "id": "seed-vc", "display_name": "Seed-VC (vc 语音转换)", "display_name_en": "Seed-VC (voice conversion)", "family": "seed_vc", "path": "models/SeedVC-MLX-GGUF", "task": "vc", "mode": "offline", "download_id": "seed_vc_mlx_q8_0", "min_vram_gb": 4 }, + { "id": "seed-vc-svc", "display_name": "Seed-VC (svc 歌声转换)", "display_name_en": "Seed-VC (singing voice conversion)", "family": "seed_vc", "path": "models/SeedVC-MLX-GGUF", "task": "svc", "mode": "offline", "download_id": "seed_vc_mlx_q8_0", "min_vram_gb": 4, "input_hint": "**Seed-VC 歌声转换 (svc)**：上传源歌声 + 目标歌手参考音色，默认 route=v1_svc（带 F0 条件）。可在『其它参数(JSON)』里调 `auto_f0_adjust` / `semi_tone_shift` / `f0_condition`。", "input_hint_en": "**Seed-VC singing conversion**: upload source singing and a target-singer reference. The default route is v1_svc with F0 conditioning." }, { "id": "rvc", "display_name": "RVC (vc, GGUF F16)", "display_name_en": "RVC (voice conversion, GGUF F16)", "family": "rvc", "path": "models/RVC-GGUF", "task": "vc", "mode": "offline", "download_id": "rvc_f16", "min_vram_gb": 4, "input_hint": "**RVC**：所选 GGUF 即目标音色；上传源语音即可转换；索引/音高等选项可用 JSON 传。", "input_hint_en": "**RVC**: the selected GGUF is the target voice; upload source speech to convert. Index and pitch options can be passed through the JSON box." }, - { "id": "miocodec", "display_name": "MioCodec (vc; codec dependency)", "family": "miocodec", "path": "models/MioCodec-25Hz-44.1kHz-v2", "task": "vc", "mode": "offline", "download_id": "miocodec_25hz_44k_v2", "min_vram_gb": 3 }, + { "id": "miocodec", "display_name": "MioCodec (vc; codec dependency)", "family": "miocodec", "path": "models/MioCodec-25Hz-44.1kHz-v2-GGUF", "task": "vc", "mode": "offline", "download_id": "miocodec_q8_0", "min_vram_gb": 3 }, { "id": "personaplex", "display_name": "PersonaPlex 7B v1 (speech conversation)", "display_name_en": "PersonaPlex 7B v1 (speech conversation)", "family": "personaplex", "path": "models/PersonaPlex-GGUF", "task": "s2s", "mode": "offline", "download_id": "personaplex_7b_v1_q4_k", "min_vram_gb": 8, "request_options": ["voice_id", "system_prompt", "temperature", "text_temperature", "top_k", "text_top_k", "do_sample", "seed"], "input_hint": "**PersonaPlex**：上传用户语音，模型返回语音回复；文本框可填写 assistant system/persona prompt；`voice_id` 选择打包音色，也可上传参考音色覆盖。", "input_hint_en": "**PersonaPlex**: upload user speech and receive a spoken response. The text box provides the assistant system/persona prompt; `voice_id` selects a packaged voice, and an uploaded reference voice overrides it." }, - { "id": "audiosr", "display_name": "AudioSR (audio super-resolution)", "family": "audiosr", "path": "models/AudioSR-GGUF/audiosr-basic-f32.gguf", "task": "s2s", "mode": "offline", "download_id": "audiosr_basic_f32", "min_vram_gb": 8, + { "id": "audiosr", "display_name": "AudioSR (audio super-resolution)", "family": "audiosr", "path": "models/AudioSR-GGUF", "task": "s2s", "mode": "offline", "download_id": "audiosr_basic_f32", "min_vram_gb": 8, "input_hint_en": "**AudioSR**: upload a source audio file to generate a super-resolved output." }, - { "id": "htdemucs", "display_name": "HTDemucs (sep 音源分离)", "display_name_en": "HTDemucs (source separation)", "family": "htdemucs", "path": "models/htdemucs", "task": "sep", "mode": "offline", "download_id": "htdemucs", "min_vram_gb": 3 }, - { "id": "bs-roformer", "display_name": "BS-RoFormer (sep 人声分离)", "display_name_en": "BS-RoFormer (vocal separation)", "family": "bs_roformer", "path": "models/BS-RoFormer-ep368-GGUF/bs-roformer-ep368-q8_0.gguf", "task": "sep", "mode": "offline", "download_id": "bs_roformer_q8_0", "min_vram_gb": 3 }, - { "id": "mel-band-roformer", "display_name": "Mel-Band RoFormer (sep 人声分离)", "display_name_en": "Mel-Band RoFormer (vocal separation)", "family": "mel_band_roformer", "path": "models/mel-roformer-mlx", "task": "sep", "mode": "offline", "download_id": "mel_band_roformer", "min_vram_gb": 3 }, + { "id": "htdemucs", "display_name": "HTDemucs (sep 音源分离)", "display_name_en": "HTDemucs (source separation)", "family": "htdemucs", "path": "models/HTDemucs-GGUF", "task": "sep", "mode": "offline", "download_id": "htdemucs_q8_0", "min_vram_gb": 3 }, + { "id": "bs-roformer", "display_name": "BS-RoFormer (sep 人声分离)", "display_name_en": "BS-RoFormer (vocal separation)", "family": "bs_roformer", "path": "models/BS-RoFormer-ep368-GGUF", "task": "sep", "mode": "offline", "download_id": "bs_roformer_q8_0", "min_vram_gb": 3 }, + { "id": "mel-band-roformer", "display_name": "Mel-Band RoFormer (sep 人声分离)", "display_name_en": "Mel-Band RoFormer (vocal separation)", "family": "mel_band_roformer", "path": "models/Mel-Band-RoFormer-GGUF", "task": "sep", "mode": "offline", "download_id": "mel_band_roformer_q8_0", "min_vram_gb": 3 }, { "id": "silero-vad", "display_name": "Silero VAD (vad, bundled)", "family": "silero_vad", "path": "assets/framework/models/silero_vad", "task": "vad", "mode": "offline", "min_vram_gb": 1 }, { "id": "marblenet-vad", "display_name": "MarbleNet VAD (vad, bundled)", "family": "marblenet_vad", "path": "assets/framework/models/marblenet_vad", "task": "vad", "mode": "offline", "min_vram_gb": 1 }, - { "id": "sortformer-diar", "display_name": "Sortformer Diarization 4spk (diar)", "family": "sortformer_diar", "path": "models/diar_sortformer_4spk-v1", "task": "diar", "mode": "offline", "download_id": "sortformer_diar_4spk_v1", "min_vram_gb": 2 }, - { "id": "qwen3-forced-aligner", "display_name": "Qwen3 Forced Aligner (align)", "family": "qwen3_forced_aligner", "path": "models/Qwen3-ForcedAligner-0.6B", "task": "align", "mode": "offline", "download_id": "qwen3_forced_aligner_0_6b", "min_vram_gb": 3 }, + { "id": "sortformer-diar", "display_name": "Sortformer Diarization 4spk (diar)", "family": "sortformer_diar", "path": "models/Sortformer-Diar-4spk-v1-GGUF", "task": "diar", "mode": "offline", "download_id": "sortformer_diar_4spk_v1_q8_0", "min_vram_gb": 2 }, + { "id": "qwen3-forced-aligner", "display_name": "Qwen3 Forced Aligner (align)", "family": "qwen3_forced_aligner", "path": "models/Qwen3-ForcedAligner-0.6B-GGUF", "task": "align", "mode": "offline", "download_id": "qwen3_forced_aligner_0_6b_q8_0", "min_vram_gb": 3 }, { "id": "muscriptor-small", "display_name": "MuScriptor Small (audio to MIDI)", "family": "muscriptor", "path": "models/MuScriptor-Small-GGUF", "task": "midi", "mode": "offline", "download_id": "muscriptor_small_f32", "min_vram_gb": 4 }, - { "id": "qwen3-tts-1.7b-vdesign", "display_name": "Qwen3-TTS 1.7B VoiceDesign (vdes)", "family": "qwen3_tts", "path": "models/Qwen3-TTS-12Hz-1.7B-VoiceDesign", "task": "vdes", "mode": "offline", "download_id": "qwen3_tts_1_7b_voice_design", "min_vram_gb": 8, + { "id": "qwen3-tts-1.7b-vdesign", "display_name": "Qwen3-TTS 1.7B VoiceDesign (vdes)", "family": "qwen3_tts", "path": "models/Qwen3-TTS-12Hz-1.7B-VoiceDesign-GGUF", "task": "vdes", "mode": "offline", "download_id": "qwen3_tts_1_7b_voicedesign_q8_0", "min_vram_gb": 8, "input_hint": "**Qwen3-TTS VoiceDesign**：在『音色描述』里用文字描述想要的声音（如“低沉磁性的中年男声，语速偏慢”），配上要念的文本即可，无需参考音频。", "input_hint_en": "**Qwen3-TTS VoiceDesign**: describe the desired voice, then enter the text to synthesize. No reference recording is required." }, - { "id": "fireredtts3-instruct-vdesign", "display_name": "FireRedTTS3 Instruct VoiceDesign", "family": "fireredtts3", "path": "models/FireRedTTS3-Instruct-GGUF/fireredtts3-instruct-q8_0.gguf", "task": "vdes", "mode": "offline", "download_id": "fireredtts3_instruct_q8_0", "min_vram_gb": 8, + { "id": "fireredtts3-instruct-vdesign", "display_name": "FireRedTTS3 Instruct VoiceDesign", "family": "fireredtts3", "path": "models/FireRedTTS3-Instruct-GGUF", "task": "vdes", "mode": "offline", "download_id": "fireredtts3_instruct_q8_0", "min_vram_gb": 8, "input_hint_en": "**FireRedTTS3 VoiceDesign**: describe the target voice in Voice description, then enter the text to synthesize." }, - { "id": "firered-audio-vdesign", "display_name": "FireRedAudio VoiceDesign", "family": "firered_audio", "path": "models/FireRedAudio-GGUF/firered-audio-q8_0.gguf", "task": "vdes", "mode": "offline", "download_id": "firered_audio_q8_0", "min_vram_gb": 10, + { "id": "firered-audio-vdesign", "display_name": "FireRedAudio VoiceDesign", "family": "firered_audio", "path": "models/FireRedAudio-GGUF", "task": "vdes", "mode": "offline", "download_id": "firered_audio_q8_0", "min_vram_gb": 10, "input_hint_en": "**FireRedAudio VoiceDesign**: describe the target voice in Voice description, then enter the text to synthesize." }, { "id": "irodori-tts-vdesign", "display_name": "Irodori-TTS v4 Small VoiceDesign (vdes 日语, GGUF Q8)", "display_name_en": "Irodori-TTS v4 Small VoiceDesign (ja vdes, GGUF Q8)", "family": "irodori_tts", "path": "models/Irodori-TTS-v4-Small-GGUF", "task": "vdes", "mode": "offline", "download_id": "irodori_tts_v4_small_q8_0", "min_vram_gb": 4, "input_hint": "**Irodori-TTS v4 VoiceDesign**（日语）：『音色描述』用日语 caption 描述音色（如「落ち着いた大人の男性。深く響く声。」），文本填要念的日语内容，无需参考音频。", "input_hint_en": "**Irodori-TTS v4 VoiceDesign**: provide a Japanese voice caption and Japanese synthesis text. No reference recording is required." },