dsh-audiogen 0.3.3 → 0.3.4
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/lib/client.js +312 -247
- package/lib/client.js.map +1 -1
- package/lib/index.js +2 -2
- package/package.json +1 -1
- package/src/agent-audio-tools.ts +2 -2
- package/src/client/AudioGenPanel.tsx +22 -0
- package/src/client/locales.ts +2 -2
- package/src/protocol.ts +1 -1
package/lib/index.js
CHANGED
|
@@ -1655,11 +1655,11 @@ function registerAgentAudioTools(ctx, resolve) {
|
|
|
1655
1655
|
},
|
|
1656
1656
|
sample_rate: {
|
|
1657
1657
|
type: "integer",
|
|
1658
|
-
description: "MiniMax
|
|
1658
|
+
description: "MiniMax sample rate: music 16000/24000/32000/44100 (default 44100); tts default 32000 (audio_setting.sample_rate)."
|
|
1659
1659
|
},
|
|
1660
1660
|
bitrate: {
|
|
1661
1661
|
type: "integer",
|
|
1662
|
-
description: "MiniMax
|
|
1662
|
+
description: "MiniMax bitrate in bps: 32000/64000/128000/256000 (music default 256000, tts default 128000; audio_setting.bitrate)."
|
|
1663
1663
|
},
|
|
1664
1664
|
channel: {
|
|
1665
1665
|
type: "integer",
|
package/package.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "dsh-audiogen",
|
|
3
3
|
"description": "AI audio generation plugin for the dsh web GUI: multi-vendor TTS/music/sound-effect channels (OpenAI-compatible, ElevenLabs, MiniMax, Stability AI and custom), per-channel model/voice catalogs, Agent tool and a sidebar AI 音频 panel.",
|
|
4
|
-
"version": "0.3.
|
|
4
|
+
"version": "0.3.4",
|
|
5
5
|
"type": "module",
|
|
6
6
|
"main": "lib/index.js",
|
|
7
7
|
"exports": {
|
package/src/agent-audio-tools.ts
CHANGED
|
@@ -119,8 +119,8 @@ export function registerAgentAudioTools(ctx: Context, resolve: () => AgentAudioT
|
|
|
119
119
|
text_normalization: { type: 'boolean', description: 'MiniMax TTS text normalization switch (voice_setting.text_normalization).' },
|
|
120
120
|
latex_read: { type: 'boolean', description: 'MiniMax TTS math formula reading switch (voice_setting.latex_read).' },
|
|
121
121
|
pronunciation_tone: { type: 'array', items: { type: 'string' }, description: 'MiniMax TTS pronunciation dictionary tone entries, each "word/pronunciation", e.g. ["处理/(chu3)(li3)", "危险/dangerous"] (pronunciation_dict.tone).' },
|
|
122
|
-
sample_rate: { type: 'integer', description: 'MiniMax
|
|
123
|
-
bitrate: { type: 'integer', description: 'MiniMax
|
|
122
|
+
sample_rate: { type: 'integer', description: 'MiniMax sample rate: music 16000/24000/32000/44100 (default 44100); tts default 32000 (audio_setting.sample_rate).' },
|
|
123
|
+
bitrate: { type: 'integer', description: 'MiniMax bitrate in bps: 32000/64000/128000/256000 (music default 256000, tts default 128000; audio_setting.bitrate).' },
|
|
124
124
|
channel: { type: 'integer', description: 'MiniMax TTS audio channels: 1 or 2, default 1 (audio_setting.channel).' },
|
|
125
125
|
force_cbr: { type: 'boolean', description: 'MiniMax TTS force CBR encoding (audio_setting.force_cbr).' },
|
|
126
126
|
subtitle_enable: { type: 'boolean', description: 'MiniMax TTS subtitle output switch (subtitle_enable).' },
|
|
@@ -266,6 +266,28 @@ export function AudioGenPanel(props: { api: AudiogenApi; scope: AudiogenScope })
|
|
|
266
266
|
<input type="checkbox" checked={instrumental} onChange={event => setInstrumental(event.target.checked)} />
|
|
267
267
|
<span>纯音乐(无歌词/人声)is_instrumental</span>
|
|
268
268
|
</label>
|
|
269
|
+
<div className={css.row}>
|
|
270
|
+
<label className={css.label}>
|
|
271
|
+
<span>采样率</span>
|
|
272
|
+
<select className={css.select} value={sampleRate} onChange={event => setSampleRate(event.target.value)}>
|
|
273
|
+
<option value="">默认(44100)</option>
|
|
274
|
+
<option value="16000">16000</option>
|
|
275
|
+
<option value="24000">24000</option>
|
|
276
|
+
<option value="32000">32000</option>
|
|
277
|
+
<option value="44100">44100</option>
|
|
278
|
+
</select>
|
|
279
|
+
</label>
|
|
280
|
+
<label className={css.label}>
|
|
281
|
+
<span>码率 bps</span>
|
|
282
|
+
<select className={css.select} value={bitrate} onChange={event => setBitrate(event.target.value)}>
|
|
283
|
+
<option value="">默认(256000)</option>
|
|
284
|
+
<option value="32000">32000</option>
|
|
285
|
+
<option value="64000">64000</option>
|
|
286
|
+
<option value="128000">128000</option>
|
|
287
|
+
<option value="256000">256000</option>
|
|
288
|
+
</select>
|
|
289
|
+
</label>
|
|
290
|
+
</div>
|
|
269
291
|
</>
|
|
270
292
|
) : null}
|
|
271
293
|
|
package/src/client/locales.ts
CHANGED
|
@@ -12,7 +12,7 @@ export const zh = {
|
|
|
12
12
|
'mode.voiceDesign': '音色设计',
|
|
13
13
|
'prompt.placeholder': '输入文本、音乐/音效描述,或音色设计描述…',
|
|
14
14
|
'prompt.required': '请输入文本或提示词',
|
|
15
|
-
'model.label': '模型
|
|
15
|
+
'model.label': '模型',
|
|
16
16
|
'voice.label': '音色',
|
|
17
17
|
'speed.label': '语速',
|
|
18
18
|
'duration.label': '时长(秒)',
|
|
@@ -113,7 +113,7 @@ export const en: Record<AudioGenKey, string> = {
|
|
|
113
113
|
'mode.voiceDesign': 'Voice design',
|
|
114
114
|
'prompt.placeholder': 'Text to speak, or a music/SFX/voice-design description…',
|
|
115
115
|
'prompt.required': 'Prompt or text is required',
|
|
116
|
-
'model.label': 'Model
|
|
116
|
+
'model.label': 'Model',
|
|
117
117
|
'voice.label': 'Voice',
|
|
118
118
|
'speed.label': 'Speed',
|
|
119
119
|
'duration.label': 'Duration (s)',
|
package/src/protocol.ts
CHANGED
|
@@ -8,7 +8,7 @@
|
|
|
8
8
|
export const AUDIOGEN_SETTINGS_NAMESPACE = 'dsh-audiogen'
|
|
9
9
|
|
|
10
10
|
/** Published package version shared by the host updater and the client UI. */
|
|
11
|
-
export const PLUGIN_VERSION = '0.3.
|
|
11
|
+
export const PLUGIN_VERSION = '0.3.4'
|
|
12
12
|
|
|
13
13
|
/** Same-origin route family (loopback-only, mirroring dsh-imagegen). */
|
|
14
14
|
export const SETTINGS_API = {
|