kugelaudio 0.2.3 → 0.4.0

package/CHANGELOG.md

@@ -1,3 +1,13 @@
+## [kugelaudio-v0.4.0](https://github.com/Kugelaudio/KugelAudio/compare/js-sdk-v0.3.0...js-sdk-v0.4.0) (2026-05-14)
+
+### Features
+
+* **web:** bump kugelaudio SDK to ^0.3.0 to enable per-project dictionary ([#640](https://github.com/Kugelaudio/KugelAudio/issues/640)) ([f503372](https://github.com/Kugelaudio/KugelAudio/commit/f5033728b2febb00cea6b021da5b5309c2c9097f))
+
+### Bug Fixes
+
+* **python-sdk,js-sdk,java-sdk:** update regional endpoints ([#660](https://github.com/Kugelaudio/KugelAudio/issues/660)) ([b9a32c0](https://github.com/Kugelaudio/KugelAudio/commit/b9a32c09813c3e9de34a9d0a84ed0e024e1fe158))
+
 # Changelog
 
 All notable changes to the KugelAudio JavaScript/TypeScript SDK will be documented in this file.
@@ -5,6 +15,21 @@ All notable changes to the KugelAudio JavaScript/TypeScript SDK will be document
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [0.3.0](https://github.com/Kugelaudio/KugelAudio/compare/js-sdk-v0.2.3...js-sdk-v0.3.0) (2026-05-10)
+
+### Features
+
+* **temperature, projectId, speed** on `tts.stream` / `tts.generate` / multi-context. Required for per-project custom dictionary replacement on the website. ([#273](https://github.com/Kugelaudio/KugelAudio/pull/273))
+* **error classification:** unify across SDKs with actionable messages ([#315](https://github.com/Kugelaudio/KugelAudio/pull/315))
+* **multi-region routing** for all SDKs ([#227](https://github.com/Kugelaudio/KugelAudio/pull/227))
+
+### Bug Fixes
+
+* **streaming session close:** per-message-quiet timeout in `StreamingSession.close()` ([#528](https://github.com/Kugelaudio/KugelAudio/pull/528))
+* **multi-context:** remove redundant `is_final` signal from protocol ([#279](https://github.com/Kugelaudio/KugelAudio/pull/279))
+* **websocket:** keep alive across streaming sessions ([#253](https://github.com/Kugelaudio/KugelAudio/pull/253))
+* **release pipeline:** fix stale repo URLs blocking semantic-release ([#637](https://github.com/Kugelaudio/KugelAudio/pull/637))
+
 ## [0.1.3] - 2024-12-25
 
 ### Fixed

package/README.md

@@ -57,6 +57,31 @@ const client = new KugelAudio({
 });
 ```
 
+### Region Selection
+
+By default, KugelAudio uses the canonical geo-routed API endpoint. You can
+select the direct EU endpoint when you need to pin traffic to Europe.
+
+| Region hint | Endpoint |
+|-------------|----------|
+| default | `api.kugelaudio.com` (geo-routed) |
+| `eu` | `api.eu.kugelaudio.com` |
+
+**Option 1 — API key prefix** (simplest, works with env vars):
+
+```typescript
+const client = new KugelAudio({ apiKey: 'eu-ka_your_api_key' });       // → EU
+const client = new KugelAudio({ apiKey: 'ka_your_api_key' });          // → canonical geo-routed API
+```
+
+**Option 2 — `region` parameter**:
+
+```typescript
+const client = new KugelAudio({ apiKey: 'ka_your_api_key', region: 'eu' });
+```
+
+The prefix is always stripped before authentication. Priority: `apiUrl` > `region` > key prefix > default.
+
 ### Single URL Architecture
 
 The SDK uses a **single URL** for both REST API and WebSocket streaming. The TTS server provides both REST endpoints (`/v1/models`, `/v1/voices`) and WebSocket (`/ws/tts`) - no proxy needed, minimal latency.
@@ -84,10 +109,10 @@ const client = new KugelAudio({
 
 ## Available Models
 
-| Model ID | Name | Parameters | Description |
-|----------|------|------------|-------------|
-| `kugel-1-turbo` | Kugel 1 Turbo | 1.5B | Fast, low-latency model for real-time applications |
-| `kugel-1` | Kugel 1 | 7B | Premium quality model for pre-recorded content |
+| Model ID | Name | Description |
+|----------|------|-------------|
+| `kugel-1-turbo` | Kugel 1 Turbo | Fast, low-latency model for real-time applications |
+| `kugel-1` | Kugel 1 | Premium quality model for pre-recorded content |
 
 ### List Available Models
 
@@ -97,7 +122,6 @@ const models = await client.models.list();
 for (const model of models) {
   console.log(`${model.id}: ${model.name}`);
   console.log(`  Description: ${model.description}`);
-  console.log(`  Parameters: ${model.parameters}`);
   console.log(`  Max Input: ${model.maxInputLength} characters`);
   console.log(`  Sample Rate: ${model.sampleRate} Hz`);
 }
@@ -213,7 +237,6 @@ await client.tts.stream(
     },
     onFinal: (stats) => {
       console.log(`Total duration: ${stats.durationMs}ms`);
-      console.log(`Time to first audio: ${stats.ttfaMs}ms`);
       console.log(`Generation time: ${stats.generationMs}ms`);
       console.log(`RTF: ${stats.rtf}`);
     },
@@ -336,10 +359,11 @@ try {
 
 ```typescript
 interface KugelAudioOptions {
-  apiKey: string;      // Required
-  apiUrl?: string;     // Default: 'https://api.kugelaudio.com'
-  ttsUrl?: string;     // Default: same as apiUrl (backend proxies to TTS)
-  timeout?: number;    // Default: 60000 (ms)
+  apiKey: string;           // Required (can be prefixed with 'eu-' for EU)
+  region?: Region;          // 'eu' selects the direct EU endpoint
+  apiUrl?: string;          // Default: https://api.kugelaudio.com
+  ttsUrl?: string;          // Default: same as apiUrl
+  timeout?: number;         // Default: 60000 (ms)
 }
 ```
 
@@ -394,7 +418,6 @@ interface GenerationStats {
   totalSamples: number;   // Total samples generated
   durationMs: number;     // Audio duration in ms
   generationMs: number;   // Generation time in ms
-  ttfaMs: number;         // Time to first audio in ms
   rtf: number;           // Real-time factor
 }
 ```
@@ -418,7 +441,6 @@ interface Model {
   id: string;             // 'kugel-1-turbo' or 'kugel-1'
   name: string;           // Human-readable name
   description: string;    // Model description
-  parameters: string;     // Parameter count ('1.5B', '7B')
   maxInputLength: number; // Maximum input characters
   sampleRate: number;     // Output sample rate
 }
@@ -499,7 +521,7 @@ async function main() {
   console.log('Available Models:');
   const models = await client.models.list();
   for (const model of models) {
-    console.log(`  - ${model.id}: ${model.name} (${model.parameters})`);
+    console.log(`  - ${model.id}: ${model.name}`);
   }
 
   // List available voices
@@ -547,4 +569,3 @@ The SDK works in modern browsers with WebSocket support. For Node.js, ensure you
 ## License
 
 MIT
-