Skip to content

Commit 29f1df4

Browse files
author
LittleMouse
committed
[update] add kokoro-1.1 model & update docs
1 parent 2adbe84 commit 29f1df4

File tree

4 files changed

+181
-124
lines changed

4 files changed

+181
-124
lines changed

doc/projects_llm_framework_doc/llm_tts_en.md

Lines changed: 67 additions & 62 deletions
Original file line numberDiff line numberDiff line change
@@ -11,24 +11,26 @@ Send JSON:
1111

1212
```json
1313
{
14-
"request_id": "2",
15-
"work_id": "tts",
16-
"action": "setup",
17-
"object": "tts.setup",
18-
"data": {
19-
"model": "single-speaker-english-fast",
20-
"response_format": "sys.pcm",
21-
"input": "tts.utf-8",
22-
"enoutput": false
23-
}
14+
"request_id": "2",
15+
"work_id": "tts",
16+
"action": "setup",
17+
"object": "tts.setup",
18+
"data": {
19+
"model": "kokoro-1.0-ax650",
20+
"response_format": "sys.pcm",
21+
"input": "tts.utf-8",
22+
"enoutput": false,
23+
"sid": 5,
24+
"speed": 1.2
25+
}
2426
}
2527
```
2628

2729
- request_id: Refer to the basic data explanation.
2830
- work_id: For configuring the unit, it is `tts`.
2931
- action: The method to call is `setup`.
3032
- object: The type of data being transmitted is `tts.setup`.
31-
- model: The model used is the `single-speaker-english-fast` English model.
33+
- model: The model used is the `kokoro-1.0-ax650` English model.
3234
- response_format: The returned result is `sys.pcm`, system audio data, which is directly sent to the llm-audio module
3335
for playback.
3436
- input: Input is `tts.utf-8`, representing user input.
@@ -38,15 +40,15 @@ Response JSON:
3840

3941
```json
4042
{
41-
"created": 1731488402,
42-
"data": "None",
43-
"error": {
44-
"code": 0,
45-
"message": ""
46-
},
47-
"object": "None",
48-
"request_id": "2",
49-
"work_id": "tts.1003"
43+
"created": 1775719938,
44+
"data": "None",
45+
"error": {
46+
"code": 0,
47+
"message": ""
48+
},
49+
"object": "None",
50+
"request_id": "2",
51+
"work_id": "tts.1008"
5052
}
5153
```
5254

@@ -60,7 +62,7 @@ Response JSON:
6062
```json
6163
{
6264
"request_id": "2",
63-
"work_id": "tts.1003",
65+
"work_id": "tts.1008",
6466
"action": "inference",
6567
"object": "tts.utf-8.stream",
6668
"data": {
@@ -80,7 +82,7 @@ Response JSON:
8082
```json
8183
{
8284
"request_id": "2",
83-
"work_id": "tts.1003",
85+
"work_id": "tts.1008",
8486
"action": "inference",
8587
"object": "tts.utf-8",
8688
"data": "What's ur name?"
@@ -99,7 +101,7 @@ Send JSON:
99101
```json
100102
{
101103
"request_id": "3",
102-
"work_id": "tts.1003",
104+
"work_id": "tts.1008",
103105
"action": "link",
104106
"object": "work_id",
105107
"data": "kws.1000"
@@ -118,7 +120,7 @@ Response JSON:
118120
},
119121
"object": "None",
120122
"request_id": "3",
121-
"work_id": "tts.1003"
123+
"work_id": "tts.1008"
122124
}
123125
```
124126

@@ -139,14 +141,16 @@ Example:
139141
"action": "setup",
140142
"object": "tts.setup",
141143
"data": {
142-
"model": "single-speaker-fast",
144+
"model": "kokoro-1.0-ax650",
143145
"response_format": "sys.pcm",
144146
"input": [
145147
"tts.utf-8",
146148
"llm.1002",
147149
"kws.1000"
148150
],
149-
"enoutput": false
151+
"enoutput": false,
152+
"sid": 5,
153+
"speed": 1.2
150154
}
151155
}
152156
```
@@ -160,7 +164,7 @@ Send JSON:
160164
```json
161165
{
162166
"request_id": "4",
163-
"work_id": "tts.1003",
167+
"work_id": "tts.1008",
164168
"action": "unlink",
165169
"object": "work_id",
166170
"data": "kws.1000"
@@ -179,7 +183,7 @@ Response JSON:
179183
},
180184
"object": "None",
181185
"request_id": "4",
182-
"work_id": "tts.1003"
186+
"work_id": "tts.1008"
183187
}
184188
```
185189

@@ -194,7 +198,7 @@ Send JSON:
194198
```json
195199
{
196200
"request_id": "5",
197-
"work_id": "llm.1003",
201+
"work_id": "tts.1008",
198202
"action": "pause"
199203
}
200204
```
@@ -211,7 +215,7 @@ Response JSON:
211215
},
212216
"object": "None",
213217
"request_id": "5",
214-
"work_id": "llm.1003"
218+
"work_id": "tts.1008"
215219
}
216220
```
217221

@@ -226,7 +230,7 @@ Send JSON:
226230
```json
227231
{
228232
"request_id": "6",
229-
"work_id": "llm.1003",
233+
"work_id": "tts.1008",
230234
"action": "work"
231235
}
232236
```
@@ -243,7 +247,7 @@ Response JSON:
243247
},
244248
"object": "None",
245249
"request_id": "6",
246-
"work_id": "llm.1003"
250+
"work_id": "tts.1008"
247251
}
248252
```
249253

@@ -258,7 +262,7 @@ Send JSON:
258262
```json
259263
{
260264
"request_id": "7",
261-
"work_id": "llm.1003",
265+
"work_id": "tts.1008",
262266
"action": "exit"
263267
}
264268
```
@@ -275,7 +279,7 @@ Response JSON:
275279
},
276280
"object": "None",
277281
"request_id": "7",
278-
"work_id": "llm.1003"
282+
"work_id": "tts.1008"
279283
}
280284
```
281285

@@ -299,17 +303,17 @@ Response JSON:
299303

300304
```json
301305
{
302-
"created": 1731652311,
303-
"data": [
304-
"tts.1003"
305-
],
306-
"error": {
307-
"code": 0,
308-
"message": ""
309-
},
310-
"object": "tts.tasklist",
311-
"request_id": "2",
312-
"work_id": "tts"
306+
"created": 1775720096,
307+
"data": [
308+
"tts.1008"
309+
],
310+
"error": {
311+
"code": 0,
312+
"message": ""
313+
},
314+
"object": "tts.tasklist",
315+
"request_id": "2",
316+
"work_id": "tts"
313317
}
314318
```
315319

@@ -320,7 +324,7 @@ Send JSON:
320324
```json
321325
{
322326
"request_id": "2",
323-
"work_id": "tts.1003",
327+
"work_id": "tts.1008",
324328
"action": "taskinfo"
325329
}
326330
```
@@ -329,22 +333,23 @@ Response JSON:
329333

330334
```json
331335
{
332-
"created": 1731652344,
333-
"data": {
334-
"enoutput": false,
335-
"inputs_": [
336-
"tts.utf-8"
337-
],
338-
"model": "single-speaker-fast",
339-
"response_format": "sys.pcm"
340-
},
341-
"error": {
342-
"code": 0,
343-
"message": ""
344-
},
345-
"object": "tts.taskinfo",
346-
"request_id": "2",
347-
"work_id": "tts.1003"
336+
"created": 1775720117,
337+
"data": {
338+
"enoutput": false,
339+
"inputs": [
340+
"tts.utf-8",
341+
"kws.1000"
342+
],
343+
"model": "kokoro-1.0-ax650",
344+
"response_format": "sys.pcm"
345+
},
346+
"error": {
347+
"code": 0,
348+
"message": ""
349+
},
350+
"object": "tts.taskinfo",
351+
"request_id": "2",
352+
"work_id": "tts.1008"
348353
}
349354
```
350355

0 commit comments

Comments
 (0)