{"adoption": {"forks": 82, "observed_at": "2026-08-28T04:04:33.625378+00:00", "stars": 1378}, "canonical_url": "https://ross.abutalabs.com/products/thinksound", "card": {"archived": false, "artifact_type": "library", "description": "[NeurIPS 2025] PyTorch implementation of [ThinkSound], a unified framework for generating audio from any modality, guided by Chain-of-Thought (CoT) reasoning.", "domain": ["artificial-intelligence", "machine-learning"], "enriched": true, "function": ["machine-learning", "audio-processing", "llm-inference", "deep-learning"], "health_score": 65, "homepage": "https://thinksound-project.github.io/", "language": "Python", "license": null, "license_family": "other", "maturity": "active", "member_repos": ["QwenAudio/ThinkSound"], "name": "QwenAudio/ThinkSound", "platform": ["python"], "pushed_at": "2026-04-03T03:07:58+00:00", "repo": "QwenAudio/ThinkSound", "stars": 1378, "tags": ["text-to-audio", "video-to-audio", "foley-sound-synthesis", "chain-of-thought", "flow-matching", "aigc-audio", "pytorch", "multimodal", "audio-editing", "research-code", "audio", "video", "natural-language-processing", "gpu", "linux"], "topics": ["aigc-audio", "foley-sound-synthesis", "text-to-audio", "text-video-to-audio", "tta", "video-to-audio"], "urls": [], "use_cases": ["generate foley sound effects for videos", "convert video into audio soundscapes", "generate audio from text descriptions", "edit audio in a video with natural language instructions", "add soundtracks to AI-generated videos", "research chain-of-thought reasoning for audio generation", "train or fine-tune video-to-audio models"], "what_it_is": "ThinkSound is a PyTorch implementation of a NeurIPS 2025 framework that generates and edits audio from video, text, or audio inputs using Chain-of-Thought reasoning from multimodal large language models to guide a flow-matching audio foundation model. It also includes the AudioCoT dataset and hosts the follow-up PrismAudio project on a separate branch.", "when_to_avoid": ["you need a production-ready, licensed product with no research code caveats (no license is specified)", "you lack GPU resources for large multimodal model inference", "you need simple text-to-speech rather than generative foley/sound effects"], "when_to_choose": ["you need state-of-the-art video-to-audio or any-to-audio generation with reasoning guidance", "you want interactive, object-centric audio refinement for video content", "you are doing research on CoT-guided audio synthesis and need the AudioCoT dataset"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/thinksound", "repo": "QwenAudio/ThinkSound", "role": "main", "score": 52}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:04:33.625378+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T04:40:21.072221+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "42e4fc2eba5676b3ee6096abfc5f46265bb8ad0e3699a3e3110ee67b7152c26c", "fetched_at": "2026-08-28T04:04:33.625378+00:00", "kind": "readme", "missing": false, "url": "https://github.com/QwenAudio/ThinkSound"}, {"content_hash": "2ad582054d062753d38e6b3386d7677c06e2d9b1aff72be32eee7b0300380232", "fetched_at": "2026-08-29T11:56:26.341313+00:00", "kind": "homepage", "missing": false, "url": "https://thinksound-project.github.io/"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:04:33.625378+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T04:40:21.072221+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "42e4fc2eba5676b3ee6096abfc5f46265bb8ad0e3699a3e3110ee67b7152c26c", "fetched_at": "2026-08-28T04:04:33.625378+00:00", "kind": "readme", "missing": false, "url": "https://github.com/QwenAudio/ThinkSound"}, {"content_hash": "2ad582054d062753d38e6b3386d7677c06e2d9b1aff72be32eee7b0300380232", "fetched_at": "2026-08-29T11:56:26.341313+00:00", "kind": "homepage", "missing": false, "url": "https://thinksound-project.github.io/"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T04:40:21.072221+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "42e4fc2eba5676b3ee6096abfc5f46265bb8ad0e3699a3e3110ee67b7152c26c", "fetched_at": "2026-08-28T04:04:33.625378+00:00", "kind": "readme", "missing": false, "url": "https://github.com/QwenAudio/ThinkSound"}, {"content_hash": "2ad582054d062753d38e6b3386d7677c06e2d9b1aff72be32eee7b0300380232", "fetched_at": "2026-08-29T11:56:26.341313+00:00", "kind": "homepage", "missing": false, "url": "https://thinksound-project.github.io/"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:04:33.625378+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:04:33.625378+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:04:33.625378+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T04:40:21.072221+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "42e4fc2eba5676b3ee6096abfc5f46265bb8ad0e3699a3e3110ee67b7152c26c", "fetched_at": "2026-08-28T04:04:33.625378+00:00", "kind": "readme", "missing": false, "url": "https://github.com/QwenAudio/ThinkSound"}, {"content_hash": "2ad582054d062753d38e6b3386d7677c06e2d9b1aff72be32eee7b0300380232", "fetched_at": "2026-08-29T11:56:26.341313+00:00", "kind": "homepage", "missing": false, "url": "https://thinksound-project.github.io/"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:04:33.625378+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:04:33.625378+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T04:40:21.072221+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "42e4fc2eba5676b3ee6096abfc5f46265bb8ad0e3699a3e3110ee67b7152c26c", "fetched_at": "2026-08-28T04:04:33.625378+00:00", "kind": "readme", "missing": false, "url": "https://github.com/QwenAudio/ThinkSound"}, {"content_hash": "2ad582054d062753d38e6b3386d7677c06e2d9b1aff72be32eee7b0300380232", "fetched_at": "2026-08-29T11:56:26.341313+00:00", "kind": "homepage", "missing": false, "url": "https://thinksound-project.github.io/"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:04:33.625378+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:04:33.625378+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:04:33.625378+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T04:40:21.072221+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "42e4fc2eba5676b3ee6096abfc5f46265bb8ad0e3699a3e3110ee67b7152c26c", "fetched_at": "2026-08-28T04:04:33.625378+00:00", "kind": "readme", "missing": false, "url": "https://github.com/QwenAudio/ThinkSound"}, {"content_hash": "2ad582054d062753d38e6b3386d7677c06e2d9b1aff72be32eee7b0300380232", "fetched_at": "2026-08-29T11:56:26.341313+00:00", "kind": "homepage", "missing": false, "url": "https://thinksound-project.github.io/"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:04:33.625378+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:04:33.625378+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T04:40:21.072221+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "42e4fc2eba5676b3ee6096abfc5f46265bb8ad0e3699a3e3110ee67b7152c26c", "fetched_at": "2026-08-28T04:04:33.625378+00:00", "kind": "readme", "missing": false, "url": "https://github.com/QwenAudio/ThinkSound"}, {"content_hash": "2ad582054d062753d38e6b3386d7677c06e2d9b1aff72be32eee7b0300380232", "fetched_at": "2026-08-29T11:56:26.341313+00:00", "kind": "homepage", "missing": false, "url": "https://thinksound-project.github.io/"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T04:40:21.072221+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "42e4fc2eba5676b3ee6096abfc5f46265bb8ad0e3699a3e3110ee67b7152c26c", "fetched_at": "2026-08-28T04:04:33.625378+00:00", "kind": "readme", "missing": false, "url": "https://github.com/QwenAudio/ThinkSound"}, {"content_hash": "2ad582054d062753d38e6b3386d7677c06e2d9b1aff72be32eee7b0300380232", "fetched_at": "2026-08-29T11:56:26.341313+00:00", "kind": "homepage", "missing": false, "url": "https://thinksound-project.github.io/"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T04:40:21.072221+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "42e4fc2eba5676b3ee6096abfc5f46265bb8ad0e3699a3e3110ee67b7152c26c", "fetched_at": "2026-08-28T04:04:33.625378+00:00", "kind": "readme", "missing": false, "url": "https://github.com/QwenAudio/ThinkSound"}, {"content_hash": "2ad582054d062753d38e6b3386d7677c06e2d9b1aff72be32eee7b0300380232", "fetched_at": "2026-08-29T11:56:26.341313+00:00", "kind": "homepage", "missing": false, "url": "https://thinksound-project.github.io/"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T04:40:21.072221+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "42e4fc2eba5676b3ee6096abfc5f46265bb8ad0e3699a3e3110ee67b7152c26c", "fetched_at": "2026-08-28T04:04:33.625378+00:00", "kind": "readme", "missing": false, "url": "https://github.com/QwenAudio/ThinkSound"}, {"content_hash": "2ad582054d062753d38e6b3386d7677c06e2d9b1aff72be32eee7b0300380232", "fetched_at": "2026-08-29T11:56:26.341313+00:00", "kind": "homepage", "missing": false, "url": "https://thinksound-project.github.io/"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 75, "longevity": 30, "rhythm": 35}, "computed_at": "2026-09-03T02:39:23.370411+00:00", "flags": ["no_releases", "no_license"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 433, "days_push": 152, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 52, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}