aliyun-cosyvoice-voice-clone

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

99installs34forks

How to install aliyun-cosyvoice-voice-clone?

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

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

Installs into the current project.

Summary

Use when creating cloned voices with Alibaba Cloud Model Studio CosyVoice customization models, especially cosyvoice-v3.5-plus or cosyvoice-v3.5-flash, from reference audio and then reusing the returned voice_id in later TTS calls.

Files · 1

View on GitHub

SKILL.md

1	Category: provider
2
3	# Model Studio CosyVoice Voice Clone
4
5	Use the CosyVoice voice enrollment API to create cloned voices from public reference audio.
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	- `cosyvoice-v2`
15
16	Recommended default in this repo:
17	- `target_model="cosyvoice-v3.5-plus"`
18
19	## Region and compatibility
20
21	- `cosyvoice-v3.5-plus` and `cosyvoice-v3.5-flash` are available only in China mainland deployment mode (Beijing endpoint).
22	- In international deployment mode (Singapore endpoint), `cosyvoice-v3-plus` and `cosyvoice-v3-flash` do not support voice clone/design.
23	- The `target_model` used during enrollment must match the model used later in speech synthesis, otherwise synthesis fails.
24
25	## Endpoint
26
27	- Domestic: `https://dashscope.aliyuncs.com/api/v1/services/audio/tts/customization`
28	- International: `https://dashscope-intl.aliyuncs.com/api/v1/services/audio/tts/customization`
29
30	## Prerequisites
31
32	- Set `DASHSCOPE_API_KEY` in your environment, or add `dashscope_api_key` to `~/.alibabacloud/credentials`.
33	- Provide a public audio URL for the enrollment sample.
34
35	## Normalized interface (cosyvoice.voice_clone)
36
37	### Request
38	- `model` (string, optional): fixed to `voice-enrollment`
39	- `target_model` (string, optional): default `cosyvoice-v3.5-plus`
40	- `prefix` (string, required): letters/digits only, max 10 chars
41	- `voice_sample_url` (string, required): public audio URL
42	- `language_hints` (array[string], optional): only first item is used
43	- `max_prompt_audio_length` (float, optional): only for `cosyvoice-v3.5-plus`, `cosyvoice-v3.5-flash`, `cosyvoice-v3-flash`
44	- `enable_preprocess` (bool, optional): only for `cosyvoice-v3.5-plus`, `cosyvoice-v3.5-flash`, `cosyvoice-v3-flash`
45
46	### Response
47	- `voice_id` (string): use this as the `voice` parameter in later TTS calls
48	- `request_id` (string)
49	- `usage.count` (number, optional)
50
51	## Operational guidance
52
53	- For Chinese dialect reference audio, keep `language_hints=["zh"]`; control dialect style later in synthesis via text or `instruct`.
54	- For `cosyvoice-v3.5-plus`, supported `language_hints` include `zh`, `en`, `fr`, `de`, `ja`, `ko`, `ru`, `pt`, `th`, `id`, `vi`.
55	- Avoid frequent enrollment calls; each call creates a new custom voice and consumes quota.
56
57	## Local helper script
58
59	Prepare a normalized request JSON:
60
61	```bash
62	python skills/ai/audio/aliyun-cosyvoice-voice-clone/scripts/prepare_cosyvoice_clone_request.py \
63	--target-model cosyvoice-v3.5-plus \
64	--prefix myvoice \
65	--voice-sample-url https://example.com/voice.wav \
66	--language-hint zh
67	```
68
69	## Validation
70
71	```bash
72	mkdir -p output/aliyun-cosyvoice-voice-clone
73	for f in skills/ai/audio/aliyun-cosyvoice-voice-clone/scripts/*.py; do
74	python3 -m py_compile "$f"
75	done
76	echo "py_compile_ok" > output/aliyun-cosyvoice-voice-clone/validate.txt
77	```
78
79	Pass criteria: command exits 0 and `output/aliyun-cosyvoice-voice-clone/validate.txt` is generated.
80
81	## Output And Evidence
82
83	- Save artifacts, command outputs, and API response summaries under `output/aliyun-cosyvoice-voice-clone/`.
84	- Include `target_model`, `prefix`, and sample URL 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-clone

99installs34forks

View on GitHub

How to install aliyun-cosyvoice-voice-clone?

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

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

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	Category: provider
2
3	# Model Studio CosyVoice Voice Clone
4
5	Use the CosyVoice voice enrollment API to create cloned voices from public reference audio.
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	- `cosyvoice-v2`
15
16	Recommended default in this repo:
17	- `target_model="cosyvoice-v3.5-plus"`
18
19	## Region and compatibility
20
21	- `cosyvoice-v3.5-plus` and `cosyvoice-v3.5-flash` are available only in China mainland deployment mode (Beijing endpoint).
22	- In international deployment mode (Singapore endpoint), `cosyvoice-v3-plus` and `cosyvoice-v3-flash` do not support voice clone/design.
23	- The `target_model` used during enrollment must match the model used later in speech synthesis, otherwise synthesis fails.
24
25	## Endpoint
26
27	- Domestic: `https://dashscope.aliyuncs.com/api/v1/services/audio/tts/customization`
28	- International: `https://dashscope-intl.aliyuncs.com/api/v1/services/audio/tts/customization`
29
30	## Prerequisites
31
32	- Set `DASHSCOPE_API_KEY` in your environment, or add `dashscope_api_key` to `~/.alibabacloud/credentials`.
33	- Provide a public audio URL for the enrollment sample.
34
35	## Normalized interface (cosyvoice.voice_clone)
36
37	### Request
38	- `model` (string, optional): fixed to `voice-enrollment`
39	- `target_model` (string, optional): default `cosyvoice-v3.5-plus`
40	- `prefix` (string, required): letters/digits only, max 10 chars
41	- `voice_sample_url` (string, required): public audio URL
42	- `language_hints` (array[string], optional): only first item is used
43	- `max_prompt_audio_length` (float, optional): only for `cosyvoice-v3.5-plus`, `cosyvoice-v3.5-flash`, `cosyvoice-v3-flash`
44	- `enable_preprocess` (bool, optional): only for `cosyvoice-v3.5-plus`, `cosyvoice-v3.5-flash`, `cosyvoice-v3-flash`
45
46	### Response
47	- `voice_id` (string): use this as the `voice` parameter in later TTS calls
48	- `request_id` (string)
49	- `usage.count` (number, optional)
50
51	## Operational guidance
52
53	- For Chinese dialect reference audio, keep `language_hints=["zh"]`; control dialect style later in synthesis via text or `instruct`.
54	- For `cosyvoice-v3.5-plus`, supported `language_hints` include `zh`, `en`, `fr`, `de`, `ja`, `ko`, `ru`, `pt`, `th`, `id`, `vi`.
55	- Avoid frequent enrollment calls; each call creates a new custom voice and consumes quota.
56
57	## Local helper script
58
59	Prepare a normalized request JSON:
60
61	```bash
62	python skills/ai/audio/aliyun-cosyvoice-voice-clone/scripts/prepare_cosyvoice_clone_request.py \
63	--target-model cosyvoice-v3.5-plus \
64	--prefix myvoice \
65	--voice-sample-url https://example.com/voice.wav \
66	--language-hint zh
67	```
68
69	## Validation
70
71	```bash
72	mkdir -p output/aliyun-cosyvoice-voice-clone
73	for f in skills/ai/audio/aliyun-cosyvoice-voice-clone/scripts/*.py; do
74	python3 -m py_compile "$f"
75	done
76	echo "py_compile_ok" > output/aliyun-cosyvoice-voice-clone/validate.txt
77	```
78
79	Pass criteria: command exits 0 and `output/aliyun-cosyvoice-voice-clone/validate.txt` is generated.
80
81	## Output And Evidence
82
83	- Save artifacts, command outputs, and API response summaries under `output/aliyun-cosyvoice-voice-clone/`.
84	- Include `target_model`, `prefix`, and sample URL 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