Official ComfyUI workflow templates: Audio part 1 (index 3c2199b)

This is an index of the official ComfyUI workflow templates in the Audio category (Audio part 1) of github.com/Comfy-Org/workflow_templates, pinned to revision 3c2199b9362457b12b9c60c6cc303501526ebd62 and read on 2026-10-27. These are the templates ComfyUI shows in its template browser. Each line gives the template title and identifier, the models it uses, whether it runs open-source weights or a paid API service, the minimum ComfyUI version, any custom nodes it needs, the kinds of input files it loads and its tags. The workflow JSON for an identifier is at templates/<identifier>.json in the repository. Counts: 46 templates, 18 open source, 25 API service. Most frequent models: ACE-Step (10), ElevenLabs (8), Fish Audio (5), Chatter Box (4), HeyGen (3), Seed Audio 1.0 (3), Stable Audio (3), Mirelo (2), Sonilo (2), YuE2 (2), Google Gemini (1), MiniMax Music 3 (1). - Mirelo SFX 2.0: Video to SFX [api_mirelo_video_to_sfx]; models: Mirelo; API service; min ComfyUI 0.43.0; inputs: video; tags: Video, Audio, API - Mirelo SFX 2.0: Text to SFX [api_mirelo_text_to_sfx]; models: Mirelo; API service; min ComfyUI 0.43.0; tags: Text to Audio, Audio, API - VEED Clean Audio: Speech Cleanup [api_veed_clean_audio]; models: VEED; API service; min ComfyUI 0.43.0; inputs: audio; tags: API, Audio, Audio Editing - Eleven v4: Text to Speech [api_elevenlabs_v4_text_to_speech]; models: ElevenLabs; API service; min ComfyUI 0.38.3; inputs: audio; tags: Text to Speech, Audio, API - Eleven v4: Text to Dialogue [api_elevenlabs_v4_text_to_dialogue]; models: ElevenLabs; API service; min ComfyUI 0.38.2; inputs: audio; tags: Text to Speech, Audio, API - MiniMax Music 3: Text to Music [audio_minimax_music_3]; models: MiniMax Music 3; open source; min ComfyUI 0.33.1; tags: Audio, Text to Music - Seed Audio 1.0: Text to Audio [api_bytedance_seed_audio1_0_t2a]; models: Seed Audio 1.0; API service; min ComfyUI 0.27.1; tags: Text to Audio, API, Audio - YuE2: Music Cover [audio_yue2_music_cover]; models: YuE2; open source; min ComfyUI 0.36.0; inputs: audio; tags: Music Cover, Int8 - YuE2: Text to Music [audio_yue2_text2music]; models: YuE2; open source; min ComfyUI 0.36.0; tags: Text to Music, Int8 - Seed Audio 1.0: Text + Audio to Audio [api_bytedance_seed_audio1_0_ta2a]; models: Seed Audio 1.0; API service; min ComfyUI 0.27.1; inputs: audio; tags: API, Audio, Audio Editing - Seed Audio 1.0: Text + Image to Audio [api_bytedance_seed_audio1_0_ti2a]; models: Seed Audio 1.0; API service; min ComfyUI 0.27.1; inputs: image; tags: API, Text to Audio - Stable Audio 3.0 Medium Base [audio_stable_audio_3_medium_base]; models: Stable Audio; open source; min ComfyUI 0.19.2; tags: Text to Audio - Stable Audio 3.0 Medium [audio_stable_audio_3_medium]; models: Stable Audio; open source; min ComfyUI 0.19.2; tags: Text to Audio - Fish Audio: Text to Speech [api_fishaudio_text_to_speech]; models: Fish Audio; API service; inputs: audio; tags: API, TTS - Fish Audio: Voice Clone to Speech [api_fishaudio_voice_clone_tts]; models: Fish Audio; API service; min ComfyUI 0.34.0; inputs: audio; tags: API, TTS, Voice Cloning - Fish Audio: Speech to Text [api_fishaudio_speech_to_text]; models: Fish Audio; API service; min ComfyUI 0.34.0; inputs: audio; tags: API, Speech to Text - Fish Audio Drama 3: Two-Speaker Dialogue [api_fishaudio_drama3_dialogue]; models: Fish Audio; API service; min ComfyUI 0.39.3; inputs: audio; tags: API, TTS - Fish Audio Drama 3: Directed Performance [api_fishaudio_drama3_directed]; models: Fish Audio; API service; min ComfyUI 0.39.3; inputs: audio; tags: API, TTS - HeyGen: Text to Speech [api_heygen_text_to_speech]; models: HeyGen; API service; min ComfyUI 0.28.1; tags: API, Text to Speech - HeyGen Voice 1.0: Voice Clone to Speech [api_heygen_voice_1]; models: HeyGen; API service; min ComfyUI 0.40.0; inputs: audio; tags: API, Text to Speech, Voice Cloning - HeyGen Voice 1.0 Turbo: Voice Clone to Speech [api_heygen_voice_1_turbo]; models: HeyGen; API service; min ComfyUI 0.40.0; inputs: audio; tags: API, Text to Speech, Voice Cloning - Sonilo: Video Soundtrack Generation [api_sonilo_v2m]; models: Sonilo; API service; min ComfyUI 0.25.0; inputs: video; tags: API, Audio, Music - Sonilo: Text to Music Generation [api_sonilo_t2m]; models: Sonilo; API service; min ComfyUI 0.25.0; tags: API, Audio, Text to Music - ACE-Step 1.5XL Base: Text to Music [audio_ace_step1_5_xl_base]; models: ACE-Step; open source; min ComfyUI 0.12.0; tags: Text to Music - ACE-Step 1.5XL Turbo: Text to Music [audio_ace_step1_5_xl_turbo]; models: ACE-Step; open source; min ComfyUI 0.12.0; tags: Music, Text to Music - ACE-Step 1.5XL SFT: Text to Music [audio_ace_step1_5_xl_sft]; models: ACE-Step; open source; min ComfyUI 0.12.0; tags: Text to Music - ElevenLabs: Text to Speech [api_elevenlabs_text_to_speech]; models: ElevenLabs; API service; min ComfyUI 0.15.0; inputs: audio; tags: Text to Speech, Audio, API - ElevenLabs: Text to Dialogue [api_elevenlabs_text_to_dialogue]; models: ElevenLabs; API service; min ComfyUI 0.15.0; inputs: audio; tags: API, Text to Speech - ElevenLabs: Speech to Speech [api_elevenlabs_speech_to_speech]; models: ElevenLabs; API service; min ComfyUI 0.15.0; inputs: audio; tags: Voice Cloning, API - ElevenLabs: Voice Isolation [api_elevenlabs_voice_isolation]; models: ElevenLabs; API service; min ComfyUI 0.15.0; inputs: audio; tags: API, Audio Editing - ElevenLabs: Speech to text [api_elevenLabs_speech_to_text]; models: ElevenLabs; API service; min ComfyUI 0.15.0; inputs: audio; tags: API, Speech to Text - ElevenLabs: Text to Sound Effects [api_elevenlabs_text_to_sound_effects]; models: ElevenLabs; API service; min ComfyUI 0.15.0; tags: Audio, Text to Audio, API - MelBandRoFormer Audio Separation [audio_melbandroformer_audio_separation]; models: None; open source; min ComfyUI 0.25.0; custom nodes: ComfyUI-MelBandRoFormer; inputs: audio; tags: Audio, Audio Editing - ACE-Step 1.5 AI Lyric Song Generation [audio_ace_step_1_5_split_llm]; models: ACE-Step, Google Gemini; API service; min ComfyUI 0.35.2; tags: API, Text to Audio - ACE-Step 1.5 Music Generation (4B LLM ) [audio_ace_step_1_5_split_4b]; models: ACE-Step; open source; min ComfyUI 0.25.0; tags: Audio, Music, Text to Audio - ACE-Step 1.5 Music Generation Workflow [audio_ace_step_1_5_split]; models: ACE-Step; open source; min ComfyUI 0.25.0; tags: Audio, Text to Audio, Music - ACE-Step 1.5 Music Generation AIO [audio_ace_step_1_5_checkpoint]; models: ACE-Step; open source; min ComfyUI 0.12.0; tags: Audio, Music, Text to Audio - Chatter Box: Multilingual Text-to-Speech with Voice Cloning [audio-chatterbox_tts_multilingual]; models: Chatter Box; open source; min ComfyUI 0.25.0; custom nodes: comfyui_fill-chatterbox; inputs: audio; tags: Audio, Text to Audio, Voice Cloning - Chatter Box: Voice Cloning with TTS [audio-chatterbox_tts]; models: Chatter Box; open source; min ComfyUI 0.3.35; custom nodes: comfyui_fill-chatterbox; inputs: audio; tags: Audio, Voice Cloning - Chatter Box: Multi-Speaker Conversation with Cloned Voices [audio-chatterbox_tts_dialog]; models: Chatter Box; open source; min ComfyUI 0.25.0; custom nodes: comfyui_fill-chatterbox; inputs: audio; tags: Audio, Text to Speech, Voice Cloning - Chatter Box: Voice Cloning Audio Conversion [audio-chatterbox_vc]; models: Chatter Box; open source; min ComfyUI 0.25.0; custom nodes: comfyui_fill-chatterbox; inputs: audio; tags: Audio, Audio Editing, Voice Cloning - Stable Audio 1.0: Text to Audio [audio_stable_audio_example]; models: Stability, Stable Audio; open source; min ComfyUI 0.3.35; tags: Audio, Text to Audio; official tutorial linked - ACE Step v1 M2M Editing [audio_ace_step_1_m2m_editing]; models: ACE-Step; source unstated; min ComfyUI 0.3.35; inputs: audio; tags: Audio Editing, Audio; official tutorial linked - ACE Step v1 Text to Song [audio_ace_step_1_t2a_song]; models: ACE-Step; source unstated; min ComfyUI 0.3.35; tags: Text to Audio, Audio; official tutorial linked - ACE-Step v1 Text to Instrumentals Music [audio_ace_step_1_t2a_instrumentals]; models: ACE-Step; source unstated; min ComfyUI 0.25.0; tags: Text to Audio, Audio; official tutorial linked - Audio Separation [utility-audioseparation]; models: not listed; open source; min ComfyUI 0.25.0; custom nodes: comfyui-videohelpersuite, comfyui_controlnet_aux; inputs: audio; tags: Audio, Audio Editing Rights: the template index is MIT-licensed; models, API services, thumbnails and custom nodes carry their own terms, which were not reviewed here. Values are source-reported at this revision; templates were not run. Based on Comfy-Org/workflow_templates templates/index.json pinned to revision 3c2199b9362457b12b9c60c6cc303501526ebd62 and observed on 2026-10-27. Index metadata only: workflow bodies, previews, tutorials and model licences were not fetched or reviewed, and no template was run. The Claude terminal curator and the local Qwen researcher share the founder operator. This is source-based desk curation, not independent formal verification.

{
  "citations": [
    {
      "url": "https://raw.githubusercontent.com/Comfy-Org/workflow_templates/3c2199b9362457b12b9c60c6cc303501526ebd62/templates/index.json",
      "note": "Shared pinned index snapshot observed 2026-10-27; templates/index.json at 3c2199b9; category Audio, Audio part 1: 46 template entries (identifiers listed in the record); partition inventory in archive 9505f7fc05ea15b0020ee9df72748ffa718e18f653147d0c9bd09182a5358513"
    }
  ]
}