# Delx HD Speech Synthesis

> Delx HD Speech Synthesis is a paid API for AI agents from api.delx.ai, paid per call via x402, $0.08/call, status unknown (last checked 2026-10-10).

Converts text to high-definition audio using the MiniMax speech-02-hd model with configurable voice, emotion, pitch, speed, and language.

## Facts

- Endpoint: POST https://api.delx.ai/api/v1/x402/speech-hd?utm_source=zero.xyz
- Price: $0.08/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-10
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/delx-hd-speech-synthesis-586b8aff
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_bbkJ-Ym2vLUHxmmvXrce0

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 delx-hd-speech-synthesis-586b8aff -d '<json body>'
```

Example prompt: Read this out loud using the English CaptivatingStoryteller voice with a happy emotion at 1.2x speed: 'Welcome to the future of AI-powered content creation — where every word comes alive.'

## When to prefer this

Choose this endpoint when you need high-definition (speech-02-hd) audio synthesis with fine-grained control over voice character, emotion, pitch, speed, and language — especially for multilingual content in English, Spanish, or Portuguese. Prefer it over standard TTS when audio quality and emotional expressiveness matter, and when per-call micropayment via x402 is acceptable.

## Known failure modes

- Text exceeds 500 UTF-8 bytes — endpoint rejects with validation error
- Invalid voice enum value — returns schema validation error
- Speed or pitch outside allowed range — returns 400 error
- Upstream Replicate/MiniMax provider failure — returns 502 or retry-exhausted error
- Payment not provided or insufficient — x402 payment required response

## How this service works

Generate high-fidelity expressive speech for $0.08 USDC. Call when you need English, Portuguese, or Spanish voiceover with emotion, speed, and pitch for up to 500 UTF-8 bytes—not a phone carrier or realtime session. Returns a validated 32 kHz mono WAV URL and SHA-256 receipt. No API key, no subscription.

## Output

Returns a JSON object containing a URL to a hosted WAV audio file (32000 Hz, 16-bit, mono), plus metadata: generation ID, model name, voice, emotion, language, pitch, speed, duration in milliseconds, byte size, SHA256 hash, input token count, and pricing details including sale price in USDC and upstream cost.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "text": {
   "type": "string",
   "maxLength": 500,
   "minLength": 1,
   "description": "Text to synthesize; the UTF-8 encoding must not exceed 500 bytes.",
   "x-maxUtf8Bytes": 500
  },
  "input": {
   "type": "string",
   "maxLength": 500,
   "minLength": 1,
   "description": "Alias for text; the UTF-8 encoding must not exceed 500 bytes.",
   "x-maxUtf8Bytes": 500
  },
  "pitch": {
   "type": "integer",
   "default": 0,
   "maximum": 12,
   "minimum": -12
  },
  "speed": {
   "type": "number",
   "default": 1,
   "maximum": 2,
   "minimum": 0.5
  },
  "voice": {
   "enum": [
    "English_Wiselady",
    "English_Deep-VoicedGentleman",
    "English_CaptivatingStoryteller",
    "Portuguese_Wiselady",
    "Portuguese_Deep-VoicedGentleman",
    "Portuguese_CaptivatingStoryteller",
    "Portuguese_Narrator",
    "Spanish_Wiselady",
    "Spanish_Deep-tonedMan",
    "Spanish_CaptivatingStoryteller",
    "Spanish_Narrator"
   ],
   "type": "string",
   "default": "English_Wiselady"
  },
  "emotion": {
   "enum": [
    "auto",
    "happy",
    "sad",
    "angry",
    "fearful",
    "disgusted",
    "surprised",
    "neutral"
   ],
   "type": "string",
   "default": "auto"
  },
  "language": {
   "enum": [
    "Automatic",
    "English",
    "French",
    "German",
    "Italian",
    "Japanese",
    "Korean",
    "Portuguese",
    "Spanish"
   ],
   "type": "string",
   "default": "Automatic"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "bytes": 588252,
  "model": "minimax/speech-02-hd",
  "pitch": 0,
  "speed": 1,
  "voice": "English_CaptivatingStoryteller",
  "sha256": "7ded32df89c15e721f6e997931b3ee28d40a89635fe35d91b5a496712e95bead",
  "emotion": "happy",
  "channels": 1,
  "language": "English",
  "provider": "replicate",
  "audio_url": "https://api.delx.ai/api/v1/generated-audio-hd/7de36cd5f5f34ef8a28904b9b5985f60.wav",
  "media_type": "audio/wav",
  "duration_ms": 9172,
  "input_tokens": 130,
  "generation_id": "7de36cd5f5f34ef8a28904b9b5985f60",
  "sample_rate_hz": 32000,
  "sale_price_usdc": 0.08,
  "gross_margin_usd": 0.067,
  "provider_attempts": 1,
  "sample_width_bits": 16,
  "upstream_cost_usd": 0.013
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/delx-hd-speech-synthesis-586b8aff/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.delx.ai](https://www.zero.xyz/host/api.delx.ai/llms.txt)