Text to speech (Piper, English voices)
From the API's own job list: GET https://api.gaents.com/v1/jobs answered HTTP 200 at 2026-11-19T06:07:32Z. Not a live reading: call it for the state now.
Text in, a WAV file (base64, 22.05 kHz mono) out. Voices: en_US-ljspeech-medium (LJ Speech, public domain), en_US-libritts_r-medium (LibriTTS-R, CC BY 4.0; 904 speakers, pick one with speaker).
Call it
curl -s https://api.gaents.com/v1/jobs/tts-piper -H "Authorization: Bearer $GAENTS_KEY" -H 'Content-Type: application/json' \
-d "{\"text\": \"Hello from gaents\"}"
Get a key on the start page or in the dashboard. MCP tool: job_tts_piper. Doors: bearer, x402, mcp.
- Unit
- call
- Charged
- measured CPU seconds of this call x our compute cost, by the 60% rule; never above the quote; no charge for an empty result or a failed run
- Price ceiling
- $0.00012536 per call (the API's
price_ceiling_usd) - Runs so far
- 1 (1 ok, 1 buyers)
- Runs
- Piper TTS (OHF-Voice/piper1-gpl, pip piper-tts) (source); licence: GPL-3.0-or-later (engine, run as a service; not distributed); voices: see settings.voice_licences
- In Proven
- Piper (OHF-Voice/piper1-gpl) (item
65e1938d2a8c42ba)
Parameters
text(string, required; max 2000 chars): the text to speakvoice(string; one of en_US-ljspeech-medium, en_US-libritts_r-medium; max 40 chars): voice (default en_US-ljspeech-medium)speaker(integer): speaker index (libritts_r only)