x402.press / services / Speech
Pending review — not for sale

Speech

AI text-to-speech — turn text into natural studio-grade audio, pay per clip in USDC or EURC.

Pending review as of 2026-10-30: retired from the fleet on 2026-10-28 and its vhost removed, so GET /health cannot complete a TLS handshake (tls_no_certificate, probed 2026-10-30T23:10Z). Nothing is for sale until a review brings it back.

What it is planned to do

Nothing here is callable today. This is the operation the review would put back on sale; the price would be measured from its handshake on the day it returns.

Operation
POST /speech/synthesize — inference, async latency
Synthesize speech from text on the qwen-audio-3.0-tts-plus model. Billed on the Exclusive tier, per clip. Returns an audio_id immediately; poll /speech/status/{audio_id} then download /speech/audio/{audio_id} (both free).
Endpoint
https://speech.x402.press/speech/synthesize
Workflows
  • speech_synthesize — Turn text into audio: POST /speech/synthesize (paid) → poll GET /speech/status/{audio_id} (free) until status is completed → GET /speech/audio/{audio_id} (free) for the clip

Free endpoints

No payment, no key — the parts a client needs before it decides to pay.

For an agent