AdsTurbo 虚拟人口播 · AdsTurbo Digital Human Voiceover
让虚拟人把文案念出来:可选平台数字人形象、用照片+声音克隆专属形象,或直接给一张人像加一段音频做对口型。含 TTS 配音与形象管理。
AdsTurbo Digital Human Voiceover
Have a virtual human avatar read a script aloud, producing a talking-head video.
When to use this skill
Use it when the user says "digital human", "voiceover", "have XX say this", "make a digital human from my photo", "lip sync", "dub", or "clone a voice".
To generate footage out of thin air (with no one speaking) use adsturbo-video-generation; to swap out the person in an existing video use adsturbo-video-transform.
Prerequisites
- Python 3.8+ (the scripts use the standard library only; nothing to install)
- An AdsTurbo account. No account yet is fine: the user can sign up or log in right in the chat with their email and a verification code, and the scripts get an API key automatically (see below)
- Optional
ADSTURBO_BASE_URL, defaulthttps://adsturbo.ai/klian/novartapi
Logging in from the chat (signs up new users too)
On first use, or when a script prints "error": "api_key_required" or hits a 401, log the user in right here instead of sending them to the website:
- Ask for the user's email and run
python3 scripts/login.py start --email <email> - If it returns
"next": "enter_captcha": show the user the image atcaptcha_url(or the local filecaptcha_file), ask them to type the characters, then runpython3 scripts/login.py captcha --code <what they typed>. The user must read and type the captcha themselves; never solve it on their behalf - Once it returns
"next": "enter_email_code", ask the user for the code AdsTurbo emailed them (check spam too) and runpython3 scripts/login.py verify --code <code> - On success the API key is saved on this machine in
~/.config/adsturbo/credentials.jsonand every script picks it up; just re-run the command that needed it
A new email is signed up automatically; an existing user is simply logged in and no duplicate key is created. login.py status shows whether a key is available; run login.py logout before switching accounts. The old way still works too: sign up at https://adsturbo.ai?channel=clawhub, create a key at https://adsturbo.ai/iris/api and export ADSTURBO_API_KEY=<key>; the environment variable takes precedence.
Every plan can call the API with an API key, and usage is billed in credits; if you run out, top up or upgrade at https://adsturbo.ai/pricing. 1080p+ video and 4K images need a subscription (credit packs alone don't count), and creating a custom digital human needs a Pro plan.
If the user is not logged in yet: do not keep retrying. First finish everything that doesn't need the API (clarify the brief, draft the script or prompt, settle aspect ratio, duration, model and other parameters, prepare the exact command), then log them in with the steps above and run the prepared command. If the captcha answer is wrong, run start again for a fresh image. Never echo the key back in a reply; script output only shows its last four characters.
First decide where the avatar comes from
This is the single fork point for picking a command:
Who does the user want speaking?
├─ Doesn't matter, pick a good-looking one → choose from the actors list → perform
├─ Use my/our own person, reused repeatedly → persona-create to register → perform
└─ Just this one image, one-off → lipsync
# Platform avatar
python3 scripts/digital_human.py actors --gender female --limit 10
python3 scripts/digital_human.py perform --actor-id act_123 --script "script content"
# Dedicated avatar (photo + optional voice cloning)
python3 scripts/digital_human.py persona-create --photo-url https://.../me.jpg --voice-audio-url https://.../voice.mp3
python3 scripts/digital_human.py perform --actor-id <returned actor_id> --script "script content"
# One-off lip sync
python3 scripts/digital_human.py lipsync --avatar-url https://.../face.jpg --audio-url https://.../voice.mp3
Full parameters in references/digital_human.md.
Hard constraint: assets must be public URLs only
None of the --photo-url, --avatar-url, --audio-url parameters accept local file paths. When the user provides a local file, upload it first:
python3 scripts/upload.py image ./portrait.jpg
python3 scripts/upload.py audio ./voice.mp3
See references/upload.md for details.
Handling async tasks
perform / persona-create / lipsync are all asynchronous. The scripts poll automatically after submission until a result is ready, so under normal conditions you can just wait.
- On timeout: use
query --workspace-id <id>to keep waiting — do not resubmit. The task is still running, and resubmitting will double-charge. - To submit without waiting: add
--no-wait - To check progress on a batch:
python3 scripts/work.py batch --workspace-ids ws_a ws_b
See references/work.md for details.
When replying to the user
- Give the result link directly — don't mention script names, command lines, JSON, or exit codes
- After submission, tell the user roughly how long to expect:
perform2–5 minutes,persona-create1–3 minutes,lipsync2–5 minutes - On error, explain the problem in one sentence, then ask whether to retry
performwill fail beforepersona-createcompletes — checkpersona-statusfirst in that case
Scope boundaries
This skill only handles "making a digital human speak". The following are out of scope — don't promise them to the user:
| User wants | Use instead |
|---|---|
| Text-to-video / image-to-video | adsturbo-video-generation |
| Replicate an existing ad | adsturbo-ad-clone |
| Watermark removal / 4K / subtitles | adsturbo-video-enhance |
| Character swap / video translation / motion control | adsturbo-video-transform |
| Image generation / e-commerce images | adsturbo-image |
AdsTurbo 虚拟人口播
让一个虚拟人形象把文案念出来,产出口播视频。
什么时候用这个 skill
用户说「数字人」「口播」「让 XX 说这段话」「用我的照片做个数字人」「对口型」「配音」「克隆声音」时用它。
要凭空生成画面(不涉及人说话)用 adsturbo-video-generation;要把已有视频里的人换掉用 adsturbo-video-transform。
前置条件
- Python 3.8+(脚本只用标准库,不需要安装依赖)
- AdsTurbo 账号。没有也行:在对话里用邮箱 + 验证码就能注册或登录,脚本自动拿到 API Key,见下
- 可选
ADSTURBO_BASE_URL,默认https://adsturbo.ai/klian/novartapi
在对话里登录(没有账号就顺便注册)
用户第一次用、或脚本输出 "error": "api_key_required" / 报 401 时,就在对话里帮用户登录,不用让他跳去网页:
- 问用户的邮箱,执行
python3 scripts/login.py start --email <邮箱> - 如果返回
"next": "enter_captcha":把captcha_url这张图(或本地文件captcha_file)给用户看,请他照图输入字符,再执行python3 scripts/login.py captcha --code <用户输入>。图形验证码必须由用户本人辨认输入,不要自己识别代填 - 返回
"next": "enter_email_code"后,请用户去邮箱(也看看垃圾箱)找 AdsTurbo 发来的验证码,执行python3 scripts/login.py verify --code <验证码> - 成功后 API Key 保存在本机
~/.config/adsturbo/credentials.json,之后所有脚本自动使用,直接重跑刚才的命令
新邮箱自动注册,老用户就是登录,不会重复创建 Key。login.py status 查看是否已登录,换账号先 login.py logout。也可以照旧在 https://adsturbo.ai?channel=clawhub 注册后到 https://adsturbo.ai/iris/api 创建 Key 并 export ADSTURBO_API_KEY=<Key>,环境变量优先。
任何套餐都能用 API Key 调用,按用量扣积分;积分不够时到 https://adsturbo.ai/pricing 充值或升级。1080p 及以上视频、4K 图片需要订阅(只买积分包不算),创建自定义数字人需要 Pro 套餐。
用户还没登录时:不要反复重试。先把不需要调接口就能做的部分做完(理清需求,写好文案或提示词,定好画幅、时长、模型等参数,拼好要执行的完整命令),再按上面的步骤在对话里登录,成功后直接执行准备好的命令。图形验证码输错时按提示重新 start 换一张图。Key 不要在回复里回显,脚本输出里只有末 4 位。
先判断形象从哪来
这是选命令的唯一分岔点:
用户想让谁来说?
├─ 无所谓,挑个好看的 → actors 列表里选 → perform
├─ 用我/我们的人,要反复用 → persona-create 建号 → perform
└─ 就这张图,一次性 → lipsync
# 平台形象
python3 scripts/digital_human.py actors --gender female --limit 10
python3 scripts/digital_human.py perform --actor-id act_123 --script "文案内容"
# 专属形象(照片 + 可选声音克隆)
python3 scripts/digital_human.py persona-create --photo-url https://.../me.jpg --voice-audio-url https://.../voice.mp3
python3 scripts/digital_human.py perform --actor-id <返回的 actor_id> --script "文案内容"
# 一次性对口型
python3 scripts/digital_human.py lipsync --avatar-url https://.../face.jpg --audio-url https://.../voice.mp3
完整参数见 references/digital_human.md。
硬约束:素材只收公网 URL
所有 --photo-url --avatar-url --audio-url 参数不接受本地文件路径。用户给本地文件时先上传:
python3 scripts/upload.py image ./portrait.jpg
python3 scripts/upload.py audio ./voice.mp3
异步任务怎么处理
perform / persona-create / lipsync 都是异步的,脚本默认提交后自动轮询到出结果,正常情况直接等即可。
- 超时了:用
query --workspace-id <id>接着等,不要重新提交——任务还在跑,重交会重复扣费 - 只想提交不等:加
--no-wait - 批量查进度:
python3 scripts/work.py batch --workspace-ids ws_a ws_b
回复用户时
- 直接给结果链接,不要提脚本名、命令行、JSON 或退出码
- 提交后告诉用户大概要等多久:
perform2–5 分钟,persona-create1–3 分钟,lipsync2–5 分钟 - 出错时用一句话说清是什么问题,再问要不要重试
persona-create完成前perform会失败,这时先查persona-status
能力边界
这个 skill 只做「让虚拟人说话」。以下不在范围内,不要向用户承诺:
| 用户想要 | 该用 |
|---|---|
| 文生视频 / 图生视频 | adsturbo-video-generation |
| 照着一条广告复刻 | adsturbo-ad-clone |
| 去水印 / 4K / 字幕 | adsturbo-video-enhance |
| 换角色 / 视频翻译 / 动作控制 | adsturbo-video-transform |
| 生成图片 / 电商图 | adsturbo-image |
- Downloads
- 922All time
- Security audit
- Review
- Last updated
- 4d ago
- Current version
- v1.4.0
- License
- MIT-0
