🎨 Text-to-Speech

Convert text to natural-sounding speech using ElevenLabs. Choose from multiple voices including different accents and styles. Returns an audio file URL in MP3 format.

Request Body

Parameter	Type	Required	Description	Default
`text`	string	required	Text to convert to speech (max 5000 chars)	—
`voice`	string	optional	Voice ID or name (e.g. Rachel, Josh, Bella)	`Rachel`

Response Fields

Field	Type	Description
`audio_url`	string	CDN URL of the generated audio file (MP3)
`voice`	string	Voice used for generation
`duration_seconds`	number	Approximate duration of the audio

Code Examples

cURL

bash

curl -X POST https://sparkforge.sh/api/tts \
  -H "Content-Type: application/json" \
  -H "X-PAYMENT: <x402-payment-token>" \
  -d '{
    "text": "Hello! Welcome to SparkForge, the API network for AI agents.",
    "voice": "Rachel"
  }'

Python

python

import requests

response = requests.post(
    "https://sparkforge.sh/api/tts",
    headers={"Content-Type": "application/json", "X-PAYMENT": "<token>"},
    json={"text": "Hello! Welcome to SparkForge.", "voice": "Rachel"}
)

data = response.json()
print(data["audio_url"])

TypeScript / Node.js

typescript

const res = await fetch402("https://sparkforge.sh/api/tts", {
  method: "POST",
  headers: { "Content-Type": "application/json" },
  body: JSON.stringify({
    text: "Hello! Welcome to SparkForge.",
    voice: "Rachel",
  }),
});

const { audio_url, duration_seconds } = await res.json();

Example Response

json

{
  "audio_url": "https://cdn.sparkforge.sh/audio/abc123.mp3",
  "voice": "Rachel",
  "duration_seconds": 3.2
}

💳 Payment via x402

This endpoint costs $0.05 per call, paid in USDC on Base, Polygon, or Solana. Use the @x402/fetch library to handle payments automatically, or implement the x402 handshake manually.

bash

# Free demo mode (no payment)
curl https://sparkforge.sh/api/tts?demo=true

# Or try via MCP (Claude Desktop, Cursor, Windsurf)
# Add to mcp config: { "url": "https://sparkforge.sh/api/mcp" }