cottom / mesh-tools

3D model tools for the platform's mesh-tools: make a provider's 3D bundle (a ZIP, or an OBJ with its MTL and textures) one GLB, or convert a GLB. The same code and limits as its Cloudflare containers, run with Node.

cottom / image-part-cut

Part cut-out for a segmentation result: fits a picture for the segmentation model, then cuts the part out of the picture's own pixels along the masks it answered, as a transparent PNG cropped to the part.

cottom / av-tools

Media probes and checks for the platform's av-tools: an upload's length, an image's decode, a video's billed seconds, a compact MP3, an export's format, a video's first or last frame. The same tools and static ffmpeg build as its Cloudflare backend.

cottom / music-video-media

Music video media tools: render a project through our renderer, split audio into segments, combine clips onto a master audio track (H.264 on the GPU encoder + AAC).

cottom / music-video-tools

Music video media tools: render a project through our renderer, split audio into segments, combine clips onto a master audio track (H.264 + AAC).

cottom / rvc-infer

AI song cover in an RVC voice: vocal, harmony and reverb separation, RVC conversion with automatic octave, reverb, key shift and mix.

cottom / rvc-train-voice-model

RVC v2 voice model training from any recordings: vocal extraction, harmony and reverb removal, denoise, breath removal, RMVPE, HuBERT, training and index.

cottom / bs-roformer

BS-RoFormer music source separation: vocals + instrumental, 4 stems or 6 stems.

cottom / vt-diarization-pyannote

VT Studio GPU ML service: diarization-pyannote contract

cottom / vt-align-qwen

VT Studio GPU ML service: align-qwen contract

cottom / vt-asr-qwen

VT Studio GPU ML service: asr-qwen contract

cottom / svc

cottom / uvr-api

cottom / vocalremover

cottom / logo-generate

cottom / adp-xxxxsdsd

cottom / isd812kksds12

cottom / xsd_​12kdsd