Find any scene in your video library.
Mixpeek understands your video, image, audio, and documents, and returns the most accurate, timestamped results from the storage you already have. Every search teaches it: relevance keeps improving the more you and your agents use it.
Explore the live demos above with zero setup: then start here when you want Mixpeek running on your own data.
Bring your own vectors
You already have embeddingsMixpeek Vector Store (MVS): an agent-native vector store that runs on your object storage. Dense, sparse, and BM25 search. From $25/mo.
Connect your files
You have raw filesManaged indexing: point us at video, audio, or documents and we extract scenes, faces, OCR, transcripts, and embeddings. No pipeline to build. From $25/mo.
What the agent sees.
Every object you index becomes structured, searchable features: faces and objects in a frame, layout regions in a document, speakers in audio. Those are the same features an agent queries, and joins across modalities.
Hover or tap a card to preview the search it powers.
Person · 0.97Face · 0.95Handbag · 0.92Video · 00:04:12“A woman carrying a tan tote bag walks past a red storefront.”
transcript · “…meet me at the corner in five.”
HeaderChartBodySignaturePDF · resume.pdfHeader, body, charts, and signature detected as typed regions.
OCR · 1 header · 3 sections · 1 signature
Who spoke when, aligned to the transcript and the timeline.
audio · 2 speakers · matched at 00:01:30
One query across every modality.
Real questions rarely fit one feature. “Find the moment our CEO said guidance while the slide read Q4 outlook” needs a face, a spoken phrase, and on-screen text to line up at the same instant.
Mixpeek ties those features to the same object and timestamp, so an agent gets back the exact clip instead of three unrelated matches.
The CEO says “guidance” as the slide behind her reads “Q4 outlook.”
"What concepts exist in my data that nobody has labeled yet?"
No keyword, example, or prompt can answer that: they all assume you already know what you're looking for. Mixpeek clusters what belongs together on its own, so a natural hierarchy surfaces instead of a flat pile of tags: a taxonomy built from your data, organized around what your business actually cares about.
That taxonomy is your ground truth, and it feeds back. Every search, every correction sharpens the features, the clusters, and the relationships. Your competitors' metadata decays. Yours compounds.
- Creative moments644
- └Unboxing214
- └Hands-on close-up121
- └Reveal + reaction93
- └Night driving88
- └Product on white342
every search + correction feeds back → sharper features, tighter clusters, truer taxonomy
In production right now.
Search video by what happens on screen
Type what you want to see, not what someone said. Every query fans out across three vector spaces (one for the picture, one for what a vision model says is happening, one for the dialogue) and reciprocal-rank fusion merges them server-side. Results are scenes with timecodes, not whole files.
Try video search →Visual search across 45k artworks
Upload any image and find visually similar paintings across 45,000+ artworks, or just describe what you're looking for. Hybrid image and text retrieval, ranked with RRF.
Try gallery search →Face search across video
Drop in a headshot and find every clip a person appears in across 63 video ads and 2,600+ faces. Full trace for takedown evidence.
Try face search →One install. Two paths.
Most retrieval stacks mean gluing together a vector DB, a file pipeline, and an agent layer. Mixpeek is one install with two ways in.
Bring embeddings
Plugs into your existing stack.
Connect your storage, point Mixpeek at it, and every file becomes searchable by what's inside it. No migration, no code changes.
Mux
Every Mux upload becomes searchable by face, scene, transcript, and on-screen text, with no manual tagging.
View integration →
Backblaze B2
S3-compatible extraction at 1/5th the cost. Store on B2, extract with Mixpeek, zero egress fees.
View integration →
Iconik
Every asset in your DAM becomes findable by what's inside it: scenes, faces, spoken words, on-screen text.
View integration →Pick your file types. Choose what to search by.
Video, image, audio, documents, text, or web: connect a bucket, pick the features you want to search by, and these pipelines run as they are. Every one is documented and open source in the extractor cookbook.
Video · Image · Audio · Text
Search by: Scenes, speech & visual similarity
Unified embeddings for video, audio, image, and text. Scene and silence chunking, Whisper transcription, thumbnails.
Multimodal (Video/Audio/Image)
Any file
Search by: Everything in one pass, any file
One extractor for image, video, audio, and documents. Auto-detects modality and applies the right pipeline.
Universal All-in-One
Image · PDF
Search by: Visual similarity, described in words
Dense 768-D image embeddings with Google SigLIP for text-to-image search in one contrastive space.
Image Embeddings (SigLIP)
Text
Search by: Meaning, not keywords, in any language
Multilingual dense text embeddings with E5-Large for semantic search and RAG out of the box.
Text Embeddings (E5-Large)
Any file
Search by: Whole objects: all their files as one
Embed ALL files of an object (images, PDFs, video, audio, text) into one 3072-D Gemini vector.
Multi-File Object Embeddings (Gemini)
Image · Video · PDF
Search by: The same face, across your whole library
Production face recognition that detects, aligns, and embeds faces to 512-D ArcFace vectors.
Face Identity (SCRFD + ArcFace)
What we shipped lately
- Aug 18APIQuery latency no longer includes the audit write that happens after your results are readyEvery successful retriever execution records an audit row. Three of the paths that write it were waiting for that write to finish before answering you: the ad-hoc execute call, the streaming execute, and the streaming ad-hoc call, one of which held the response generator open for the duration. The row describes a query that has already run, so nothing in your results depends on it, and a slow moment in the analytics store was being added to the latency of a search that was otherwise complete. Worse, two of those sites would have turned an analytics outage into a failed query. All three now write in the background. Billing is unaffected either way, because it is metered on a separate record rather than on this one, and the error path still records synchronously so a failure is never lost.
- Aug 18StudioThe plan page now links to the cost estimator instead of leaving you to find itA new organization landing on the plan page is being asked to choose a price, and the only thing in the header was a log-out link. The estimator that answers the question already existed, and a gated organization could already open it, so the missing piece was an affordance pointing at it rather than any new capability. The link is now on the page where the decision is made.
- Aug 18StudioForking a showcase app now carries that context through signupClicking "fork this into your Studio" on a showcase sent you to the plan page with generic copy that never mentioned what you had just forked. Two different fork paths reach that page and they arrive carrying their context differently: a marketplace fork keeps it in the URL, while a canvas fork passes through an intermediate redirect that drops the query string before the page renders. Only the first was being read, so the second arrived looking like an ordinary signup. The plan page now reads both, names the showcase you came from, and states that the fork is applied immediately after checkout.
- Aug 17APIInspect an external export and validate your mapping before importing anythingTwo endpoints open the collection-import path. POST /v1/collections/import/infer takes a sample of an external export, reads the source fields and their types, and returns a suggested source-to-target mapping for the collection you are importing into. POST /v1/collections/import/validate-mapping takes the finalized mapping and checks it against that collection: a missing root-identity mapping, source and target types that disagree, vector dimensions that do not line up with a known index, and source fields that resolve to nothing. Both run on the sample alone and write no data, so you can iterate on a mapping without creating documents you then have to clean up.
From $25/mo. Usage-based everything.
Two products, one model: a monthly minimum that acts as a floor, with usage above it billed at the same transparent rates. MVS is priced by the vector, Managed by the object.
Bring your own embeddings and pay by the vector. Dense, sparse, and BM25 search on your own object storage. Build starts at $25/mo with up to 1M vectors; Scale ($250/mo) covers 25M.
Start with MVSBring raw objects and pay by the object: credits at $0.001 cover extraction, embedding, indexing, enrichment, and retrieval. Build covers 100K objects/mo; Scale ($250/mo) covers 1M.
Start with ManagedDedicated infrastructure, self-hosted options, SSO, SLA, security reviews, and hands-on architecture support.
Talk to usCommon questions.
Do I have to move my data?
No. Mixpeek reads from your existing S3, GCS, R2, Azure, or S3-compatible bucket. Your storage stays the system of record, and nothing leaves your cloud.
How fast is retrieval?
Hybrid queries (dense, sparse, and BM25) return in well under 100ms p95, even with vectors persisted on object storage rather than held in RAM.
Do I need embeddings to start?
No. Bring your own vectors with MVS, or point Managed at raw files and it generates embeddings and features for you.
What can Managed extract?
Faces, scenes, transcripts, OCR, labels, and embeddings from video, images, audio, PDFs, and documents, all indexed at the object level.
Can I self-host?
Yes. Deploy in your own cloud (BYO-Cloud) with SOC 2-ready and HIPAA-ready controls, SSO, audit trails, and namespaces.
How does pricing work?
Both MVS and Managed start at $25/mo minimum. Usage counts toward the minimum: pay the greater of metered usage or the floor. MVS bills storage + queries; Managed bills in credits covering extraction, embedding, indexing, and retriever execution.