# Rengi Forge: Voice Audio Processor

> Rengi Forge: Voice Audio Processor is a paid API for AI agents from rengi.dev, paid per call via x402, $0.1/call, status unknown (last checked 2026-10-22).

Processes a voice recording or TTS take into game-ready audio: high-pass filter, noise reduction, de-essing, loudness normalization to -18 LUFS / -1 dBTP, and optional phrase splitting with a CSV cue sheet.

## Facts

- Endpoint: POST https://rengi.dev/v1/audio-tools/voice?utm_source=zero.xyz
- Price: $0.1/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-22
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/rengi-forge-voice-audio-processor-7cd9363f
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_Iaq_WyvJFugh8iXRZLRxr

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 rengi-forge-voice-audio-processor-7cd9363f -d '<json body>'
```

Example prompt: Take this voice recording and make it game-ready: reduce noise at strength 0.6, normalize to -18 LUFS, split it into one file per phrase (minimum 400ms silence between phrases), and give me the output as OGG files with a CSV cue sheet.

## When to prefer this

Choose this endpoint when you need to prepare voice recordings or TTS audio for use inside a game engine (Unity, Godot, etc.) and want a single-step pipeline that handles noise reduction, loudness normalization to game VO standards (-18 LUFS), de-essing, and automatic phrase splitting with a cue sheet — rather than chaining multiple separate audio tools.

## Known failure modes

- Audio file exceeds size or duration limits — returns an error indicating the file is too large
- Neither 'audio' nor 'audioUrl' provided — returns a validation error
- Unreachable or invalid audioUrl — returns a fetch error
- Denoise value out of 0–1 range — schema validation error
- targetLufs outside -30 to -10 range — schema validation error
- minSilenceMs outside 100–3000 range — schema validation error
- Audio format not recognized or corrupted — returns a decode error
- Payment not included or insufficient — 402 Payment Required response

## How this service works

Audio tools: Make a voice recording or TTS take game-ready: rumble high-passed, noise reduced against the measured floor, sibilance tamed, dialogue loudness (-18 LUFS) with a -1 dBTP ceiling, and a long take split into one file per phrase with a CSV cue sheet. Full schema: https://rengi.dev/v1/audio-tools/schema

## Output

One or more processed audio files (OGG, WAV, or MP3) with high-pass filtering applied, noise reduction at the requested strength, sibilance controlled, and loudness normalized to the target LUFS (-18 by default) with a -1 dBTP ceiling. If split is enabled, each detected phrase is returned as a separate file along with a CSV cue sheet mapping phrase indices to timing data.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "audio": {
   "type": "string",
   "description": "Audio file as base64 (wav, mp3, ogg, flac, m4a)."
  },
  "split": {
   "type": "boolean",
   "default": true,
   "description": "One file per phrase."
  },
  "format": {
   "enum": [
    "ogg",
    "wav",
    "mp3"
   ],
   "type": "string",
   "default": "ogg"
  },
  "denoise": {
   "type": "number",
   "default": 0.5,
   "maximum": 1,
   "minimum": 0,
   "description": "0 gentle, 1 strong. Strong denoising can make a voice sound metallic."
  },
  "audioUrl": {
   "type": "string",
   "format": "uri",
   "description": "Audio file URL."
  },
  "targetLufs": {
   "type": "number",
   "default": -18,
   "maximum": -10,
   "minimum": -30,
   "description": "Dialogue loudness; -18 LUFS is a common game VO target."
  },
  "minSilenceMs": {
   "type": "integer",
   "default": 350,
   "maximum": 3000,
   "minimum": 100,
   "description": "A pause at least this long separates two phrases."
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/rengi-forge-voice-audio-processor-7cd9363f/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from rengi.dev](https://www.zero.xyz/host/rengi.dev/llms.txt)