@breeze.blue/sdk 0.14.0 → 0.16.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/CHANGELOG.md +10 -0
- package/README.md +6 -1
- package/dist/client.js +5 -3
- package/dist/types.d.ts +2 -3
- package/dist/version.d.ts +1 -1
- package/dist/version.js +1 -1
- package/dist/voice-metadata.d.ts +1 -1
- package/dist/voice-metadata.js +1 -1
- package/package.json +1 -1
package/CHANGELOG.md
CHANGED
|
@@ -1,5 +1,15 @@
|
|
|
1
1
|
# Changelog
|
|
2
2
|
|
|
3
|
+
## 0.16.0
|
|
4
|
+
|
|
5
|
+
- Clone previews use an automatically generated script in the reference audio language. Custom text, instructions, and language hints are not accepted.
|
|
6
|
+
- Breaking: remove `text`, `instructions`, `languageCode`, and `previewLanguageCode` from `voices.createClonePreview(...)` calls. Use Text to Speech with a saved voice for custom scripts and performance instructions.
|
|
7
|
+
|
|
8
|
+
## 0.15.0
|
|
9
|
+
|
|
10
|
+
- Added `previewLanguageCode` to Voice Clone previews independently of the reference audio language hint.
|
|
11
|
+
- Expanded voice language metadata for the Multilingual-51 model.
|
|
12
|
+
|
|
3
13
|
## 0.14.0
|
|
4
14
|
|
|
5
15
|
- Added `account.currentApiKey()` for checking the authenticating key's status
|
package/README.md
CHANGED
|
@@ -454,7 +454,6 @@ const clonePreview = await client.voices.createClonePreview({
|
|
|
454
454
|
filename: "sample.wav",
|
|
455
455
|
contentType: "audio/wav",
|
|
456
456
|
},
|
|
457
|
-
text: "This is a short preview script.",
|
|
458
457
|
});
|
|
459
458
|
let generatedVoiceId = clonePreview.generatedVoiceId;
|
|
460
459
|
|
|
@@ -573,3 +572,9 @@ try {
|
|
|
573
572
|
```
|
|
574
573
|
|
|
575
574
|
Each API error exposes `status`, `code`, `detail`, `meta`, and `headers`.
|
|
575
|
+
|
|
576
|
+
Clone previews automatically generate a short script in the detected reference audio language. They accept a reference sample, name, and optional description. Save the preview as a voice, then use Text to Speech for custom scripts, instructions, or target languages.
|
|
577
|
+
|
|
578
|
+
### HTTP TTS speed
|
|
579
|
+
|
|
580
|
+
Pass `voiceSettings: { speed: 1.25 }` to control speech speed without changing pitch, from 0.5 to 2.0. Omission always means 1.0; saved voice speed is not inherited. Sync, async and HTTP streaming support this parameter; Realtime does not.
|
package/dist/client.js
CHANGED
|
@@ -1727,12 +1727,14 @@ function clonePreviewForm(request) {
|
|
|
1727
1727
|
if (request.removeBackgroundNoise) {
|
|
1728
1728
|
throw new BreezeBlueConfigurationError("removeBackgroundNoise is not supported by the Breeze Developer API.");
|
|
1729
1729
|
}
|
|
1730
|
+
for (const field of ["text", "instructions", "languageCode", "previewLanguageCode"]) {
|
|
1731
|
+
if (field in request) {
|
|
1732
|
+
throw new BreezeBlueConfigurationError(`Clone previews do not accept ${field}; the script and language are generated automatically.`);
|
|
1733
|
+
}
|
|
1734
|
+
}
|
|
1730
1735
|
const form = new FormData();
|
|
1731
1736
|
form.set("name", request.name);
|
|
1732
1737
|
appendOptional(form, "description", request.description);
|
|
1733
|
-
appendOptional(form, "language_code", request.languageCode);
|
|
1734
|
-
appendOptional(form, "text", request.text);
|
|
1735
|
-
appendOptional(form, "instructions", request.instructions);
|
|
1736
1738
|
for (const file of normalizeFiles(request.file, request.files, { required: true })) {
|
|
1737
1739
|
appendFile(form, "files", file);
|
|
1738
1740
|
}
|
package/dist/types.d.ts
CHANGED
|
@@ -230,6 +230,7 @@ export interface VoiceSettings {
|
|
|
230
230
|
similarityBoost?: number;
|
|
231
231
|
style?: number;
|
|
232
232
|
useSpeakerBoost?: boolean;
|
|
233
|
+
/** Request-only, pitch-preserving HTTP TTS speed (0.5–2.0). Omitted means 1.0. */
|
|
233
234
|
speed?: number;
|
|
234
235
|
guidanceScale?: number | null;
|
|
235
236
|
}
|
|
@@ -300,6 +301,7 @@ export interface Model {
|
|
|
300
301
|
}
|
|
301
302
|
export interface Voice {
|
|
302
303
|
voiceId: string;
|
|
304
|
+
/** Account display name, including a personal alias for a saved public voice. */
|
|
303
305
|
name: string;
|
|
304
306
|
origin: string;
|
|
305
307
|
voiceType: string;
|
|
@@ -390,9 +392,6 @@ export interface VoiceClonePreviewRequest {
|
|
|
390
392
|
files?: Array<UploadData | UploadFile>;
|
|
391
393
|
description?: string;
|
|
392
394
|
removeBackgroundNoise?: boolean;
|
|
393
|
-
languageCode?: VoiceLanguageCode;
|
|
394
|
-
text?: string;
|
|
395
|
-
instructions?: string;
|
|
396
395
|
}
|
|
397
396
|
export interface VoiceClonePreview {
|
|
398
397
|
generatedVoiceId: string;
|
package/dist/version.d.ts
CHANGED
|
@@ -1,2 +1,2 @@
|
|
|
1
|
-
export declare const SDK_VERSION = "0.
|
|
1
|
+
export declare const SDK_VERSION = "0.16.0";
|
|
2
2
|
export declare const SDK_NAME = "@breeze.blue/sdk";
|
package/dist/version.js
CHANGED
|
@@ -1,2 +1,2 @@
|
|
|
1
|
-
export const SDK_VERSION = "0.
|
|
1
|
+
export const SDK_VERSION = "0.16.0";
|
|
2
2
|
export const SDK_NAME = "@breeze.blue/sdk";
|
package/dist/voice-metadata.d.ts
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
export declare const VOICE_GENDER_CODES: readonly ["male", "female", "neutral"];
|
|
2
2
|
export declare const VOICE_AGE_CODES: readonly ["child", "young", "middle_aged", "old"];
|
|
3
3
|
export declare const VOICE_TONE_CODES: readonly ["warm", "calm", "bright", "gentle", "energetic", "authoritative", "sincere", "weary", "precise", "refined", "urgent", "friendly", "articulate", "steady", "playful", "compassionate", "reflective", "measured", "rhythmic", "passionate"];
|
|
4
|
-
export declare const VOICE_LANGUAGE_CODES: readonly ["ar", "cs", "de", "el", "en", "es", "fi", "fr", "hi", "id", "it", "ja", "ko", "nl", "pl", "pt", "ro", "ru", "th", "tr", "uk", "vi", "zh"];
|
|
4
|
+
export declare const VOICE_LANGUAGE_CODES: readonly ["af", "ar", "bg", "bn", "bs", "ca", "cs", "da", "de", "el", "en", "es", "et", "eu", "fa", "fi", "fr", "gl", "he", "hi", "hu", "id", "is", "it", "ja", "kn", "ko", "lt", "mr", "ms", "ne", "nl", "no", "pl", "pt", "ro", "ru", "sk", "sl", "sq", "sv", "sw", "ta", "te", "th", "tl", "tr", "uk", "ur", "vi", "zh"];
|
|
5
5
|
export declare const VOICE_TONE_MAX_ITEMS: 3;
|
|
6
6
|
export declare const VOICE_ACCENT_CODES_BY_LANGUAGE: {
|
|
7
7
|
readonly en: readonly ["american", "british", "scottish", "irish", "australian", "canadian", "us_southern", "us_new_york", "indian", "south_african", "russian", "japanese", "korean", "chinese"];
|
package/dist/voice-metadata.js
CHANGED
|
@@ -2,7 +2,7 @@
|
|
|
2
2
|
export const VOICE_GENDER_CODES = ["male", "female", "neutral"];
|
|
3
3
|
export const VOICE_AGE_CODES = ["child", "young", "middle_aged", "old"];
|
|
4
4
|
export const VOICE_TONE_CODES = ["warm", "calm", "bright", "gentle", "energetic", "authoritative", "sincere", "weary", "precise", "refined", "urgent", "friendly", "articulate", "steady", "playful", "compassionate", "reflective", "measured", "rhythmic", "passionate"];
|
|
5
|
-
export const VOICE_LANGUAGE_CODES = ["ar", "cs", "de", "el", "en", "es", "fi", "fr", "hi", "id", "it", "ja", "ko", "nl", "pl", "pt", "ro", "ru", "th", "tr", "uk", "vi", "zh"];
|
|
5
|
+
export const VOICE_LANGUAGE_CODES = ["af", "ar", "bg", "bn", "bs", "ca", "cs", "da", "de", "el", "en", "es", "et", "eu", "fa", "fi", "fr", "gl", "he", "hi", "hu", "id", "is", "it", "ja", "kn", "ko", "lt", "mr", "ms", "ne", "nl", "no", "pl", "pt", "ro", "ru", "sk", "sl", "sq", "sv", "sw", "ta", "te", "th", "tl", "tr", "uk", "ur", "vi", "zh"];
|
|
6
6
|
export const VOICE_TONE_MAX_ITEMS = 3;
|
|
7
7
|
export const VOICE_ACCENT_CODES_BY_LANGUAGE = {
|
|
8
8
|
en: ["american", "british", "scottish", "irish", "australian", "canadian", "us_southern", "us_new_york", "indian", "south_african", "russian", "japanese", "korean", "chinese"],
|