# TTSAudit - TTS Audio Quality Assurance API

> TTSAudit - TTS Audio Quality Assurance API is a paid API for AI agents from api.ttsaudit.com, paid per call via x402, $0.01/call, status unknown (last checked 2026-09-15).

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.

## Facts

- Endpoint: GET https://api.ttsaudit.com/v1/audit
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/ttsaudit-tts-audio-quality-assurance-api-e859f79b
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_qeOeGDeovApsQ1dHW30eb

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability ttsaudit-tts-audio-quality-assurance-api-e859f79b
```

Example prompt: 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?

## When to prefer this

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.

## Known failure modes

- 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

## How this service works

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.

## Output

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.

## Request schema (JSON Schema)

```json
{
 "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"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "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"
     }
    ]
   }
  ]
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/ttsaudit-tts-audio-quality-assurance-api-e859f79b/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.ttsaudit.com](https://www.zero.xyz/host/api.ttsaudit.com/llms.txt)