{"uid":"cap_CSJGRv19GpyUxnD1xtUmv","slug":"halowerk-voice-clone-check-embedding-similarity-scorer-2b1cfd2a","name":"Halowerk Voice Clone Check — Embedding Similarity Scorer","description":"Calculates cosine similarity between caller-supplied numeric embeddings and combines it with supplied spectral distance, pitch-contour correlation and timing distance using fixed weights. It processes no audio and cannot establish speaker identity, consent, cloning, authenticity or fraud.","url":"https://creator.halowerk.com/v1/voice-clone-check","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"candidate_embedding":{"type":"array","items":{"type":"number","maximum":1000000,"minimum":-1000000},"maxItems":4096,"minItems":2},"reference_embedding":{"type":"array","items":{"type":"number","maximum":1000000,"minimum":-1000000},"maxItems":4096,"minItems":2},"timing_distance_0_1":{"type":"number","maximum":1,"minimum":0},"spectral_distance_0_1":{"type":"number","maximum":1,"minimum":0},"pitch_contour_correlation":{"type":"number","maximum":1,"minimum":-1}}},"responseSchema":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.003","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"probe","requiresHandshake":false,"reviewCount":0,"rating":{"score":"0.00","successRate":"0.00","reviews":0,"stars":null,"state":"unrated"},"availabilityStatus":"unknown","priceObserved":null,"sessionDeposit":null,"pricing":{"kind":"static","summary":"$0.003/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.003","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.003","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_6CQadp8Lx-b493A0PMCqB","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.003","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Computes a weighted similarity score between two numeric voice embeddings combined with caller-supplied spectral distance, pitch-contour correlation, and timing distance to produce a composite voice-match score.","exampleAgentPrompt":"Score how similar these two speaker embeddings are: my reference embedding is [0.12, -0.45, 0.78, ...] and the candidate is [0.11, -0.43, 0.80, ...], with spectral distance 0.2, pitch-contour correlation 0.85, and timing distance 0.15.","exampleUseCases":[{"title":"Voice Feature Similarity Pipeline","prompt":"I've extracted embeddings from two audio clips — reference: [0.3, -0.7, 0.5, 0.2] and candidate: [0.31, -0.68, 0.52, 0.19] — and computed spectral distance 0.1, pitch-contour correlation 0.92, and timing distance 0.05. Can you give me a weighted composite similarity score?"},{"title":"Multi-Feature Voice Match Scoring","prompt":"Combine these precomputed voice features into one score for me: the two speaker embeddings I'll pass, spectral distance is 0.35, pitch-contour correlation is 0.60, and timing distance is 0.4. I need the composite match value."},{"title":"Research Embedding Distance Aggregation","prompt":"I have four-dimensional reference and candidate voice embeddings from my experiment and separately computed spectral distance 0.25, pitch correlation 0.75, and timing distance 0.3 — can you run them through the weighted similarity scorer and give me the combined result?"}],"resultDescription":"Returns a composite voice-match score derived from the cosine similarity between the two supplied numeric embeddings, combined with the caller-provided spectral distance, pitch-contour correlation, and timing distance using fixed internal weights. Does not process audio, infer speaker identity, or determine authenticity.","failureModes":["Mismatched embedding lengths between candidate and reference vectors return a validation error","Values outside allowed ranges (e.g. spectral_distance_0_1 > 1 or pitch_contour_correlation < -1) are rejected","Embeddings with fewer than 2 or more than 4096 elements are rejected","Missing required fields result in an error response","Numeric overflow from extreme embedding values near ±1,000,000 may cause computation errors"],"whenToPreferThis":"Use this endpoint when you have already extracted numeric voice embeddings and supplementary feature distances (spectral, pitch, timing) externally and need a fast, deterministic weighted composite similarity score. Do not use it to process raw audio, identify speakers, detect clones, assess consent, or flag fraud — it performs only numeric aggregation of caller-supplied features.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-13T12:37:25.565Z","isFirstParty":false}