Delta TTS API

A small HTTP API for private voice cloning and local speech synthesis.

Authentication

Send your anonymous token in Authorization: Bearer YOUR_TOKEN. An explicit header takes precedence over the browser cookie.

Create a voice

curl -X POST https://tts.deltaservers.nl/api/v1/voices \
+-H "Authorization: Bearer YOUR_TOKEN" \
+-F "name=My Voice" -F "language=English" -F "consent=true" \
+-F "reference_text=Exact transcript" -F "reference_audio=@reference.wav"

Voice endpoints

GET /api/v1/voices
GET /api/v1/voices/{voice_id}
DELETE /api/v1/voices/{voice_id}

Generate speech

curl -X POST https://tts.deltaservers.nl/api/v1/audio/speech \
+  -H "Authorization: Bearer YOUR_TOKEN" \
+  -H "Content-Type: application/json" \
+  -d '{"voice":"voice_xxx","text":"Hello world","format":"mp3"}' \
+  --output speech.mp3

POST /api/v1/generate stores audio and returns JSON. POST /api/v1/audio/speech returns the audio bytes directly. The compatibility alias is POST /v1/audio/speech.

JavaScript

const response = await fetch("https://tts.deltaservers.nl/api/v1/audio/speech", {
  method: "POST",
  headers: { Authorization: "Bearer YOUR_TOKEN", "Content-Type": "application/json" },
  body: JSON.stringify({ voice: "voice_xxx", text: "Hello world", format: "mp3" })
});
const audio = await response.arrayBuffer();

Python

import requests
r = requests.post("https://tts.deltaservers.nl/api/v1/audio/speech",
  headers={"Authorization": "Bearer YOUR_TOKEN"},
  json={"voice":"voice_xxx", "text":"Hello world", "format":"mp3"})
open("speech.mp3", "wb").write(r.content)

Errors

Errors use {"success":false,"error":{"code":"...","message":"..."}}. Common codes: INVALID_TOKEN, VOICE_NOT_FOUND, TEXT_TOO_LONG, QUEUE_FULL, MODEL_UNAVAILABLE, and RATE_LIMITED.

OpenAPI JSON →