# Delx Kokoro Speech

> Delx Kokoro Speech is a paid API for AI agents from api.delx.ai, paid per call via x402, $0.002/call, status unknown (last checked 2026-09-16).

Converts text to speech audio using the Kokoro TTS model, returning a durable audio URL and SHA-256 receipt, paid per-clip via x402 micropayment at $0.001 USDC.

## Facts

- Endpoint: POST https://api.delx.ai/api/v1/x402/speech
- Price: $0.002/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-16
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/delx-kokoro-speech-ff84cc6e
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_Nob6_4ZSwCW1GxDinqcMW

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-kokoro-speech-ff84cc6e -d '<json body>'
```

Example prompt: Read this aloud using the af_sarah voice at normal speed and give me a link to the audio clip: 'Welcome to our platform. We're glad you're here.'

## When to prefer this

Choose this endpoint when you need ultra-low-cost per-clip TTS ($0.001 USDC) without an API key or subscription, especially for AI agent workflows that call TTS sporadically. It is ideal when you need a durable audio URL and a verifiable SHA-256 receipt for auditability. Prefer it over subscription TTS services when usage is low-volume or unpredictable. Use when Kokoro voice quality meets your needs and you want x402 micropayment integration.

## Known failure modes

- Text exceeds 500-character limit — request rejected with validation error
- Payment via x402 fails or USDC balance insufficient — returns 402 Payment Required
- Invalid voice enum value — returns schema validation error
- Speed value outside 0.5–2.0 range — rejected with parameter error
- Empty or missing text field — returns 400 Bad Request
- Network timeout during synthesis — may return 503 or timeout error

## How this service works

Delx Commerce text to speech API for agents at $0.002 USDC. Call when you need short narration, voiceover, IVR prompts, or notification clips without a TTS subscription. Kokoro WAV + SHA-256 via x402 on Base. Accepts native `text` or OpenAI-shaped `input`/`voice`/`speed` (up to 500 characters). Not a phone carrier or realtime voice session.

## Output

Returns a durable audio URL pointing to the synthesized speech clip, a SHA-256 receipt confirming payment and content integrity, and metadata about the voice and parameters used. The audio URL is persistent and can be linked or embedded directly.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "text": {
   "type": "string",
   "maxLength": 500,
   "minLength": 1,
   "description": "Text to synthesize into a short speech clip."
  },
  "input": {
   "type": "string",
   "maxLength": 500,
   "minLength": 1,
   "description": "OpenAI-compatible alias for `text`."
  },
  "model": {
   "enum": [
    "kokoro",
    "kokoro-82m",
    "tts-1"
   ],
   "type": "string",
   "default": "kokoro",
   "description": "`tts-1` is accepted as a compatibility alias; delivery uses Kokoro 82M."
  },
  "speed": {
   "type": "number",
   "default": 1,
   "maximum": 2,
   "minimum": 0.5
  },
  "voice": {
   "enum": [
    "af_bella",
    "af_nicole",
    "af_sarah",
    "am_fenrir",
    "am_michael",
    "bf_emma",
    "bm_george",
    "ff_siwis",
    "hf_alpha",
    "hm_omega",
    "alloy",
    "echo",
    "fable",
    "onyx",
    "nova",
    "shimmer"
   ],
   "type": "string",
   "default": "af_bella"
  },
  "response_format": {
   "enum": [
    "wav"
   ],
   "type": "string",
   "default": "wav",
   "description": "The hosted result is currently delivered as WAV."
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "bytes": 48128,
  "model": "jaaari/kokoro-82m",
  "speed": 1,
  "voice": "af_bella",
  "sha256": "cb45a6e6fa30b28b791a6256f9f522f13fc9c6de5b407030bd853cab62523d63",
  "channels": 1,
  "provider": "replicate",
  "audio_url": "https://api.delx.ai/api/v1/generated-audio/0de6f22023df47f4a96c260bd980257a.wav",
  "media_type": "audio/wav",
  "duration_ms": 1000,
  "generation_id": "0de6f22023df47f4a96c260bd980257a",
  "sample_rate_hz": 24000,
  "sale_price_usdc": 0.002,
  "provider_attempts": 1,
  "sample_width_bits": 16,
  "prompt_policy_version": "raw/v1"
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/delx-kokoro-speech-ff84cc6e/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)