Quickstart
Three steps to your first take. Create an account, generate an API key under API Keys, then call the generate endpoint:
curl -X POST "https://api.lucidweights.ai/v1/tts/file-inference" \
-H "x-api-key: lw_YOUR_SECRET" \
-H "Content-Type: application/json" \
-d '{
"text": "The model is not just reading this. It is deciding how it should sound.",
"speaker": "kabir",
"language": "en",
"output_format": "pcm_24000"
}' \
--output take.wavRun sends this exact request from your browser to api.lucidweights.ai. If the browser blocks cross-origin requests, copy the code and run it from your terminal instead.
A successful response is raw audio bytes (audio/wav here) with generation time reported in the X-Reverie-Latency-Ms header. The free plan includes 25,000 credits a month (1 credit = 1 TTS character or 1 second of STT audio).