## Performance evidence update / 18 September 2026 MODALITY PERFORMANCE / EVIDENCE REVIEWED 18 SEPTEMBER 2026 Define the useful result. Measure the complete job. A modality-specific timing is not yet linked to this guide. There may be supporting engineering measurements in the internal archive. We are reconciling their workload, result quality and comparison conditions before presenting a public chart. A benchmark for an adjacent model does not establish this model’s performance. 01 Original / metadata fidelity 02 Import-to-usable time 03 Decode & derived-data cost Include memory, storage, energy and hardware writes # Media | 8DB Product reference. Reviewed 18 September 2026. Implementation and evaluation scope are stated below. Explore the models (https://8braid.com/modalities) / 8DB Media Make content part of the answer. Connect media representations to metadata, source material and supported search paths within a broader data workflow. Explore the capabilities See a complete workload Represent · relate · retrieve Model / Media Conceptual diagram [Diagram: media representation: conceptual diagram] Image, audio and frame sequences carry different representations that can connect to one source record. Capabilities What changes Input to value Alternatives Performance Adoption Related articles Reference Start with the operations your question needs. Typed media schemas Registered decomposers for supported formats Relationships to source events and derived representations Documented product scope, reviewed 17 September 2026. The underlying build and deployment must be qualified for your application. Format support varies. Transcription, semantic interpretation and embedding generation require appropriate codecs or models. A database that stores media does not automatically perform those tasks. Connected native models Keep the next question within reach. The broader value is to connect a photograph or recording to what it documents. Media, time, location, text and relationships can become parts of one question instead of unrelated retrieval results. [Diagram: documents representation: conceptual diagram] Documents Keep the source behind the answer. Structure · search · trace Explore model ↗ (https://8braid.com/modalities/documents) [Diagram: vectors representation: conceptual diagram] Vectors Give a similar result its context. Compare · rank · retrieve Explore model ↗ (https://8braid.com/modalities/vectors) [Diagram: time series representation: conceptual diagram] Time series Keep the meaning in every observation. Observe · window · analyze Explore model ↗ (https://8braid.com/modalities/time-series) These connections show the models involved in the application design. Compare the supported combination and full workflow with a realistic alternative. Input → usable value / interactive design example Assemble the evidence from a recorded inspection 0 1 Receive a recording → 0 2 Derive representations → 0 3 Keep source links → 0 4 Retrieve segments → 0 5 Review the evidence → [Diagram: media representation: conceptual diagram] Step 1 / Media Receive a recording with capture time and asset identity Image, audio and frame sequences carry different representations that can connect to one source record. Next: Derive representations Conceptual application workflow. Qualify the supported operations, external tools, protection and persistence for the complete path. These diagrams are explanatory, not measured results. Read the complete workflow and comparison scope Receive a recording with capture time and asset identity Decode or derive representations with the required tools Store supported content and source relationships Retrieve relevant segments, text and nearby observations Return an inspection view with linked evidence Count model/codec work, index readiness, transfer and consumer rendering when they belong to the input-to-value contract. Fewer data handoffs may help, but end-to-end latency and energy need measurement. Compare a realistic alternative. Integrated data platforms and specialist media/model pipelines are both relevant. Select the smallest realistic stack for the required output rather than assuming each media type requires a separate database. SurrealDB data models (https://surrealdb.com/docs/learn/data-models) Compare equivalent outputs and required guarantees, including the simplest single-product alternative where one exists. A specialist may remain the better fit when its operators, ecosystem or operational maturity are decisive. Combining native models becomes valuable when your actual question crosses them. Performance & resources Measure the work that delivers the answer. Supported format/round-trip fidelity; segment relevance; derivation time; model/codec cost; source alignment; end-to-end latency; bytes and joules per completed job. This draft does not assign a new speed ratio or score to this modality. Existing measurements and source leads are retained in the evidence programme; a qualified public result must identify the particular operation and path tested. Explore the published benchmark evidence (https://8braid.com/benchmarks) What belongs inside the timer and resource budget? For input-to-value testing, declare the input state and the consumer-ready output first. Include parsing, derivation, storage/protection, index readiness, querying, result assembly and delivery as applicable. Identify amortized setup and any work deferred past the finish line. Report database-stage and full-job results separately. Do not add unrelated medians or p95 values, or multiply component speedups into a claimed workflow result. Energy needs measured joules; reduced handoffs alone do not establish a saving. Choose the path that fits your deployment. Verify the supported API/SDK, data format, persistence and indexing behaviour for the release you plan to use. Match the operation-by-modality protection profile and device qualification to the workload. Post-quantum protection (https://8braid.com/pqc) · Plan a workload evaluation (https://8braid.com/build) Related articles Take the next step into the thinking. Mechanism & application Give Your AI the Evidence Behind the Answer (https://8braid.com/journal/the-database-is-part-of-the-model) Explore the ideas and implementation context behind this capability. Mechanism & application One Sealed Store for Every Shape of Data, and It Works With the Network Gone (https://8braid.com/journal/one-store-for-many-shapes-disconnected) Explore the ideas and implementation context behind this capability. Reference / Reviewed 17 September 2026 Readable, shareable and traceable. This reference explains 8DB’s public modality description (https://8braid.com/modalities#explore) with an explicit workload and selection criteria. It is a documentary review, not fresh execution of every operator or platform. Public sources: 8DB modality scope (https://8braid.com/modalities) ; SurrealDB data models (https://surrealdb.com/docs/learn/data-models) ; the related articles above. Internal source leads and outstanding release checks remain in the editorial record. Download this reference (https://8braid.com/modality-reference/media.md) Evaluate the question your application needs to answer. Bring the data shapes, input state, expected output and the systems you use today. Define a comparison around that complete job. Discuss your workload (https://8braid.com/build)