aliyun-videoretalk

Name: aliyun-videoretalk
Author: cinience

397stars34forks

How to install aliyun-videoretalk?

cinience/alicloud-skills/aliyun-videoretalk

$npx -y skills add cinience/alicloud-skills --skill aliyun-videoretalk

Installs into the current project.

Summary

Use when replacing lip sync in existing videos with Alibaba Cloud Model Studio VideoRetalk (videoretalk). Use when creating dubbed videos, replacing narration, or synchronizing a talking-head video to a new speech track.

Files · 1

View on GitHub

SKILL.md

1	Category: provider
2
3	# Model Studio VideoRetalk
4
5	## Validation
6
7	```bash
8	mkdir -p output/aliyun-videoretalk
9	python -m py_compile skills/ai/video/aliyun-videoretalk/scripts/prepare_retalk_request.py && echo "py_compile_ok" > output/aliyun-videoretalk/validate.txt
10	```
11
12	Pass criteria: command exits 0 and `output/aliyun-videoretalk/validate.txt` is generated.
13
14	## Output And Evidence
15
16	- Save normalized request payloads, target face selection settings, and task polling snapshots under `output/aliyun-videoretalk/`.
17	- Record the exact video/audio input URLs and whether `video_extension` was enabled.
18
19	Use VideoRetalk when the input is already a person video and the job is to replace lip sync with a new speech track.
20
21	## Critical model names
22
23	Use this exact model string:
24	- `videoretalk`
25
26	## Prerequisites
27
28	- This model currently only supports China mainland (Beijing).
29	- API is HTTP async only; there is no online console experience.
30	- Set `DASHSCOPE_API_KEY` in your environment, or add `dashscope_api_key` to `~/.alibabacloud/credentials`.
31
32	## Normalized interface (video.retalk)
33
34	### Request
35	- `model` (string, optional): default `videoretalk`
36	- `video_url` (string, required)
37	- `audio_url` (string, required)
38	- `ref_image_url` (string, optional): target face when input video contains multiple faces
39	- `video_extension` (bool, optional): extend video to match longer audio
40	- `query_face_threshold` (int, optional): `120` to `200`
41
42	### Response
43	- `task_id` (string)
44	- `task_status` (string)
45	- `video_url` (string, when finished)
46	- `usage` (object, optional)
47
48	## Endpoint and execution model
49
50	- Submit task: `POST https://dashscope.aliyuncs.com/api/v1/services/aigc/image2video/video-synthesis/`
51	- Poll task: `GET https://dashscope.aliyuncs.com/api/v1/tasks/{task_id}`
52	- HTTP calls are async only and must set header `X-DashScope-Async: enable`.
53
54	## Quick start
55
56	```bash
57	python skills/ai/video/aliyun-videoretalk/scripts/prepare_retalk_request.py \
58	--video-url "https://example.com/talking-head.mp4" \
59	--audio-url "https://example.com/new-voice.wav" \
60	--video-extension
61	```
62
63	## Operational guidance
64
65	- Keep input videos front-facing and close enough for stable face tracking.
66	- If the video contains multiple faces, provide `ref_image_url` to anchor the intended target.
67	- If the new audio is longer than the input video, decide explicitly whether to extend the picture track or truncate the audio.
68	- URLs must be public HTTP/HTTPS links; local file paths are not accepted by the API.
69
70	## Output location
71
72	- Default output: `output/aliyun-videoretalk/request.json`
73	- Override base dir with `OUTPUT_DIR`.
74
75	## References
76
77	- `references/sources.md`

People who liked this also viewed

6 picks

Type

aliyun-videoretalk

397stars34forks

View on GitHub

How to install aliyun-videoretalk?

cinience/alicloud-skills/aliyun-videoretalk

$npx -y skills add cinience/alicloud-skills --skill aliyun-videoretalk

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	Category: provider
2
3	# Model Studio VideoRetalk
4
5	## Validation
6
7	```bash
8	mkdir -p output/aliyun-videoretalk
9	python -m py_compile skills/ai/video/aliyun-videoretalk/scripts/prepare_retalk_request.py && echo "py_compile_ok" > output/aliyun-videoretalk/validate.txt
10	```
11
12	Pass criteria: command exits 0 and `output/aliyun-videoretalk/validate.txt` is generated.
13
14	## Output And Evidence
15
16	- Save normalized request payloads, target face selection settings, and task polling snapshots under `output/aliyun-videoretalk/`.
17	- Record the exact video/audio input URLs and whether `video_extension` was enabled.
18
19	Use VideoRetalk when the input is already a person video and the job is to replace lip sync with a new speech track.
20
21	## Critical model names
22
23	Use this exact model string:
24	- `videoretalk`
25
26	## Prerequisites
27
28	- This model currently only supports China mainland (Beijing).
29	- API is HTTP async only; there is no online console experience.
30	- Set `DASHSCOPE_API_KEY` in your environment, or add `dashscope_api_key` to `~/.alibabacloud/credentials`.
31
32	## Normalized interface (video.retalk)
33
34	### Request
35	- `model` (string, optional): default `videoretalk`
36	- `video_url` (string, required)
37	- `audio_url` (string, required)
38	- `ref_image_url` (string, optional): target face when input video contains multiple faces
39	- `video_extension` (bool, optional): extend video to match longer audio
40	- `query_face_threshold` (int, optional): `120` to `200`
41
42	### Response
43	- `task_id` (string)
44	- `task_status` (string)
45	- `video_url` (string, when finished)
46	- `usage` (object, optional)
47
48	## Endpoint and execution model
49
50	- Submit task: `POST https://dashscope.aliyuncs.com/api/v1/services/aigc/image2video/video-synthesis/`
51	- Poll task: `GET https://dashscope.aliyuncs.com/api/v1/tasks/{task_id}`
52	- HTTP calls are async only and must set header `X-DashScope-Async: enable`.
53
54	## Quick start
55
56	```bash
57	python skills/ai/video/aliyun-videoretalk/scripts/prepare_retalk_request.py \
58	--video-url "https://example.com/talking-head.mp4" \
59	--audio-url "https://example.com/new-voice.wav" \
60	--video-extension
61	```
62
63	## Operational guidance
64
65	- Keep input videos front-facing and close enough for stable face tracking.
66	- If the video contains multiple faces, provide `ref_image_url` to anchor the intended target.
67	- If the new audio is longer than the input video, decide explicitly whether to extend the picture track or truncate the audio.
68	- URLs must be public HTTP/HTTPS links; local file paths are not accepted by the API.
69
70	## Output location
71
72	- Default output: `output/aliyun-videoretalk/request.json`
73	- Override base dir with `OUTPUT_DIR`.
74
75	## References
76
77	- `references/sources.md`

People who liked this also viewed

6 picks

Type