x402.press ElevenLabs
simple-inference

ElevenLabs

ElevenLabs text-to-speech — render text with expressive, multi-language voices, pay per clip in USDC or EURC. No ElevenLabs account or API key required.

elevenlabsspeechtext-to-speechttsaudiovoiceaix402

What is ElevenLabs?

ElevenLabs text-to-speech behind x402 micropayments. POST /synthesize accepts text, an ElevenLabs voice ID and a model, and returns an audio_id in about a second. Two models are offered: eleven_v4 (up to 2,000 characters, the most expressive) and eleven_v4_turbo (up to 4,000 characters, the real-time variant). Voices come from the service's own ElevenLabs account catalogue — list them at GET /voices, including cloned and workspace voices. Output formats: mp3 (default), wav, pcm, opus, with optional sample rate and speech speed. Clips are stored for 2 hours after generation — poll GET /status/{audio_id} (free) and download via GET /audio/{audio_id} (free).

Pay per call in USDC, EURC across Base, Arbitrum, Polygon, Avalanche, Ethereum, Robinhood and Arc via the x402 micropayment protocol — no subscriptions, no API keys, no wallets to configure for the caller.

Operations

inference

MethodEndpointDescriptionTier
POST/synthesizeSynthesize speech with an ElevenLabs voice. Billed on the Exclusive tier, per clip. eleven_v4 accepts up to 2,000 characters; eleven_v4_turbo up to 4,000. Returns an audio_id immediately; poll /status/{audio_id} then download /audio/{audio_id} (both free).exclusive

Workflows

Data sources

Examples

synthesize

Speak a short English announcement with the account's default ElevenLabs voice

{
  "text": "Welcome to the x402 ElevenLabs service.",
  "model_id": "eleven_v4",
  "format": "mp3"
}