aliyun-cosyvoice-voice-design

Name: aliyun-cosyvoice-voice-design
Author: cinience

49installs34forks

How to install aliyun-cosyvoice-voice-design?

cinience/alicloud-skills/aliyun-cosyvoice-voice-design

$npx -y skills add cinience/alicloud-skills --skill aliyun-cosyvoice-voice-design

Installs into the current project.

Summary

Use when designing custom voices with Alibaba Cloud Model Studio CosyVoice customization models, especially cosyvoice-v3.5-plus or cosyvoice-v3.5-flash, from a voice prompt plus preview text before using the returned voice_id in TTS.

Files · 1

View on GitHub

SKILL.md

1	Category: provider
2
3	# Model Studio CosyVoice Voice Design
4
5	Use the CosyVoice voice enrollment API to create designed voices from a natural-language voice description.
6
7	## Critical model names
8
9	Use `model="voice-enrollment"` and one of these `target_model` values:
10	- `cosyvoice-v3.5-plus`
11	- `cosyvoice-v3.5-flash`
12	- `cosyvoice-v3-plus`
13	- `cosyvoice-v3-flash`
14
15	Recommended default in this repo:
16	- `target_model="cosyvoice-v3.5-plus"`
17
18	## Region and compatibility
19
20	- `cosyvoice-v3.5-plus` and `cosyvoice-v3.5-flash` are available only in China mainland deployment mode (Beijing endpoint).
21	- In international deployment mode (Singapore endpoint), `cosyvoice-v3-plus` and `cosyvoice-v3-flash` do not support voice clone/design.
22	- The `target_model` must match the later speech synthesis model.
23
24	## Endpoint
25
26	- Domestic: `https://dashscope.aliyuncs.com/api/v1/services/audio/tts/customization`
27	- International: `https://dashscope-intl.aliyuncs.com/api/v1/services/audio/tts/customization`
28
29	## Prerequisites
30
31	- Set `DASHSCOPE_API_KEY` in your environment, or add `dashscope_api_key` to `~/.alibabacloud/credentials`.
32
33	## Normalized interface (cosyvoice.voice_design)
34
35	### Request
36	- `model` (string, optional): fixed to `voice-enrollment`
37	- `target_model` (string, optional): default `cosyvoice-v3.5-plus`
38	- `prefix` (string, required): letters/digits only, max 10 chars
39	- `voice_prompt` (string, required): max 500 chars, Chinese or English only
40	- `preview_text` (string, required): max 200 chars, Chinese or English
41	- `language_hints` (array[string], optional): `zh` or `en`, and should match `preview_text`
42	- `sample_rate` (int, optional): e.g. `24000`
43	- `response_format` (string, optional): e.g. `wav`
44
45	### Response
46	- `voice_id` (string)
47	- `request_id` (string)
48	- `status` (string, optional)
49
50	## Operational guidance
51
52	- Keep `voice_prompt` concrete: timbre, age range, pace, emotion, articulation, and scenario.
53	- If `language_hints` is used, it should match the language of `preview_text`.
54	- Designed voice names include a `-vd-` marker in the generated backend naming convention.
55
56	## Local helper script
57
58	Prepare a normalized request JSON:
59
60	```bash
61	python skills/ai/audio/aliyun-cosyvoice-voice-design/scripts/prepare_cosyvoice_design_request.py \
62	--target-model cosyvoice-v3.5-plus \
63	--prefix announcer \
64	--voice-prompt "沉稳的中年男性播音员，低沉有磁性，语速平稳，吐字清晰。" \
65	--preview-text "各位听众朋友，大家好，欢迎收听晚间新闻。" \
66	--language-hint zh
67	```
68
69	## Validation
70
71	```bash
72	mkdir -p output/aliyun-cosyvoice-voice-design
73	for f in skills/ai/audio/aliyun-cosyvoice-voice-design/scripts/*.py; do
74	python3 -m py_compile "$f"
75	done
76	echo "py_compile_ok" > output/aliyun-cosyvoice-voice-design/validate.txt
77	```
78
79	Pass criteria: command exits 0 and `output/aliyun-cosyvoice-voice-design/validate.txt` is generated.
80
81	## Output And Evidence
82
83	- Save artifacts, command outputs, and API response summaries under `output/aliyun-cosyvoice-voice-design/`.
84	- Include `target_model`, `prefix`, `voice_prompt`, and `preview_text` in the evidence file.
85
86	## References
87
88	- `references/api_reference.md`
89	- `references/sources.md`

People who liked this also viewed

6 picks

Type

aliyun-cosyvoice-voice-design

49installs34forks

View on GitHub

How to install aliyun-cosyvoice-voice-design?

cinience/alicloud-skills/aliyun-cosyvoice-voice-design

$npx -y skills add cinience/alicloud-skills --skill aliyun-cosyvoice-voice-design

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	Category: provider
2
3	# Model Studio CosyVoice Voice Design
4
5	Use the CosyVoice voice enrollment API to create designed voices from a natural-language voice description.
6
7	## Critical model names
8
9	Use `model="voice-enrollment"` and one of these `target_model` values:
10	- `cosyvoice-v3.5-plus`
11	- `cosyvoice-v3.5-flash`
12	- `cosyvoice-v3-plus`
13	- `cosyvoice-v3-flash`
14
15	Recommended default in this repo:
16	- `target_model="cosyvoice-v3.5-plus"`
17
18	## Region and compatibility
19
20	- `cosyvoice-v3.5-plus` and `cosyvoice-v3.5-flash` are available only in China mainland deployment mode (Beijing endpoint).
21	- In international deployment mode (Singapore endpoint), `cosyvoice-v3-plus` and `cosyvoice-v3-flash` do not support voice clone/design.
22	- The `target_model` must match the later speech synthesis model.
23
24	## Endpoint
25
26	- Domestic: `https://dashscope.aliyuncs.com/api/v1/services/audio/tts/customization`
27	- International: `https://dashscope-intl.aliyuncs.com/api/v1/services/audio/tts/customization`
28
29	## Prerequisites
30
31	- Set `DASHSCOPE_API_KEY` in your environment, or add `dashscope_api_key` to `~/.alibabacloud/credentials`.
32
33	## Normalized interface (cosyvoice.voice_design)
34
35	### Request
36	- `model` (string, optional): fixed to `voice-enrollment`
37	- `target_model` (string, optional): default `cosyvoice-v3.5-plus`
38	- `prefix` (string, required): letters/digits only, max 10 chars
39	- `voice_prompt` (string, required): max 500 chars, Chinese or English only
40	- `preview_text` (string, required): max 200 chars, Chinese or English
41	- `language_hints` (array[string], optional): `zh` or `en`, and should match `preview_text`
42	- `sample_rate` (int, optional): e.g. `24000`
43	- `response_format` (string, optional): e.g. `wav`
44
45	### Response
46	- `voice_id` (string)
47	- `request_id` (string)
48	- `status` (string, optional)
49
50	## Operational guidance
51
52	- Keep `voice_prompt` concrete: timbre, age range, pace, emotion, articulation, and scenario.
53	- If `language_hints` is used, it should match the language of `preview_text`.
54	- Designed voice names include a `-vd-` marker in the generated backend naming convention.
55
56	## Local helper script
57
58	Prepare a normalized request JSON:
59
60	```bash
61	python skills/ai/audio/aliyun-cosyvoice-voice-design/scripts/prepare_cosyvoice_design_request.py \
62	--target-model cosyvoice-v3.5-plus \
63	--prefix announcer \
64	--voice-prompt "沉稳的中年男性播音员，低沉有磁性，语速平稳，吐字清晰。" \
65	--preview-text "各位听众朋友，大家好，欢迎收听晚间新闻。" \
66	--language-hint zh
67	```
68
69	## Validation
70
71	```bash
72	mkdir -p output/aliyun-cosyvoice-voice-design
73	for f in skills/ai/audio/aliyun-cosyvoice-voice-design/scripts/*.py; do
74	python3 -m py_compile "$f"
75	done
76	echo "py_compile_ok" > output/aliyun-cosyvoice-voice-design/validate.txt
77	```
78
79	Pass criteria: command exits 0 and `output/aliyun-cosyvoice-voice-design/validate.txt` is generated.
80
81	## Output And Evidence
82
83	- Save artifacts, command outputs, and API response summaries under `output/aliyun-cosyvoice-voice-design/`.
84	- Include `target_model`, `prefix`, `voice_prompt`, and `preview_text` in the evidence file.
85
86	## References
87
88	- `references/api_reference.md`
89	- `references/sources.md`

People who liked this also viewed

6 picks

Type