Overview
AudioMind AI provides text‑to‑speech with controllable emotions, realtime streaming, and voice cloning. Use REST for batch synthesis or WebSocket for interactive experiences.
Quickstart
Synthesize a short line with emotion controls using a REST example.
# 1) Set your API key
export AUDIOMIND_API_KEY="<YOUR_KEY>"
# 2) Create an audio file (example endpoint)
curl -X POST https://api.audiomind.tech/v1/tts \
-H "Authorization: Bearer $AUDIOMIND_API_KEY" \
-H "Content-Type: application/json" \
-o out.mp3 \
-d '{
"text": "Welcome to AudioMind.",
"voice": "Nova",
"emotion": { "valence": 0.5, "arousal": 0.5 },
"format": "mp3"
}'
Realtime (WebSocket)
// Pseudocode outline
ws = new WebSocket("wss://api.audiomind.tech/v1/stream")
ws.onopen = () => ws.send(JSON.stringify({
type: "start",
auth: { token: "<API_KEY>" },
voice: "Nova",
emotion: { valence: 0.7, arousal: 0.6 }
}))
ws.onmessage = (evt) => {/* audio chunks */}
For more endpoints and SDKs, contact us.