{"uid":"cap_qeOeGDeovApsQ1dHW30eb","slug":"ttsaudit-tts-audio-quality-assurance-api-e859f79b","name":"TTSAudit - TTS Audio Quality Assurance API","description":"Automated quality assurance for Text-to-Speech audio. Submit a batch of Text-to-Speech files and get a per-file anomaly report - voice drift, glitches, accent shifts - so you regenerate only the bad ones.","url":"https://api.ttsaudit.com/v1/audit","method":"GET","headers":{},"bodySchema":{"type":"object","properties":{"pace":{"enum":["true","false"],"type":"string","description":"Run pacing/WPM analysis"},"files":{"type":"array","items":{"type":"string","format":"binary"},"description":"Audio files to audit (multipart/form-data)"},"quality":{"enum":["true","false"],"type":"string","description":"Run per-track quality analysis (SNR, clipping, artifacts)"},"X-Wallet":{"type":"string","description":"Optional header (not a body field). Pass the payer wallet address ahead of the 402 response so previously-audited files return at the cached price (0.2 credits = $0.002 per analysis). Must match the wallet that signs the x402 payment."},"accuracy":{"enum":["standard","high","highest"],"type":"string","description":"Transcription accuracy tier (default: standard)"},"comparison":{"enum":["true","false"],"type":"string","description":"Run cross-file similarity analysis"},"customLabel":{"type":"string","description":"Optional human-readable label (max 120 chars) shown in the dashboard sidebar to help identify this audit. Useful for batches keyed by your own job IDs."},"scriptAccuracy":{"enum":["true","false"],"type":"string","description":"Run transcript-vs-script accuracy analysis"}}},"responseSchema":{"type":"json","example":{"score":82,"checks":{"quality":{"score":75,"summary":"2 tracks with noticeable artifacts."},"comparison":{"score":90,"summary":"Good consistency across files."}},"timing":{"total":4.2},"auditId":"abc123","summary":"3 of 5 files flagged for regeneration.","fileCount":5,"reportUrl":"https://ttsaudit.com/dashboard?tab=audit&session=abc123","regenCount":3,"creditsUsed":10,"tracksToRegenerate":[{"file":"track_03.wav","reasons":[{"check":"quality","message":"High artifact count"}]}]}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.01","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"settled","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":"$0.01/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.01","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.01","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_yPRwa_Npa_-7M5vvEra-q","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.01","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Analyzes a batch of Text-to-Speech audio files and returns a per-file anomaly report identifying voice drift, glitches, accent shifts, pacing issues, and transcript accuracy problems.","exampleAgentPrompt":"Can you audit these 5 TTS audio files for quality issues — run quality analysis, pacing, and cross-file comparison at high accuracy, and label the batch 'product-launch-v2' so I can find it in the dashboard later?","exampleUseCases":null,"resultDescription":"A JSON object containing an overall audit score, per-check sub-scores (quality, comparison, pacing, script accuracy), a list of specific files flagged for regeneration with the reasons why, a report URL for the dashboard, the number of credits used, and total processing time. For example: 3 of 5 files flagged, with track_03.wav identified as having high artifact count.","failureModes":["Unsupported audio format returns an error — ensure files are in a supported binary audio format like WAV or MP3","Payment not completed via x402 results in a 402 Payment Required response before audit runs","Invalid or missing audio files array causes a 400 Bad Request","scriptAccuracy enabled without a reference script may return incomplete results","Files exceeding size limits may be rejected","Wallet address mismatch between X-Wallet header and signing wallet may prevent cached pricing"],"whenToPreferThis":"Choose this endpoint when you have a batch of AI-generated TTS audio files that need quality gating before publication — especially when you want to identify only the bad files for regeneration rather than re-rendering everything. It is ideal for production pipelines producing large volumes of TTS content (e.g. audiobooks, voice UI, e-learning) where catching artifacts, pacing errors, voice drift, or script deviations early saves regeneration cost. Prefer this over manual listening or generic audio analysis tools when you need structured, per-file reports with actionable regeneration recommendations.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-15T18:36:59.503Z","isFirstParty":false}