Back to Details

chat-with-anyone

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Chat with Anyone

与任何人聊天

Chat with any real person or fictional character in their own voice by automatically finding their speech online, extracting a clean reference sample, and using it to generate replies.

通过自动在网络上查找角色的公开语音、提取干净的参考样本并用来生成回复，你可以用任何真实人物或虚构角色原本的声音与其聊天。

Triggers

触发词

我想跟xxx聊天 (I want to chat with xxx)
你来扮演xxx跟我说话 (Play the role of xxx and talk to me)
让xxx给我讲讲这篇文章 (Let xxx explain this article to me)
用xxx的声音说 (Say this in xxx's voice)
Talk to me like xxx
Roleplay as xxx

我想跟xxx聊天 (I want to chat with xxx)
你来扮演xxx跟我说话 (Play the role of xxx and talk to me)
让xxx给我讲讲这篇文章 (Let xxx explain this article to me)
用xxx的声音说 (Say this in xxx's voice)
Talk to me like xxx
Roleplay as xxx

Workflow

工作流

When the user asks you to roleplay or chat as a specific character, follow these steps exactly:

当用户要求你扮演特定角色或和特定角色聊天时，请严格遵循以下步骤：

1. Character Disambiguation

1. 角色消歧

If the user's description is ambiguous (e.g., "US President", "Spider-Man actor"), ask for clarification first to determine the exact person or specific portrayal they want.

如果用户的描述存在歧义（例如“美国总统”、“蜘蛛侠演员”），请先要求用户澄清，确认他们想要的具体人物或特定演绎版本。

2. Find a Reference Video

2. 查找参考视频

Use your web search capabilities to find a YouTube, Bilibili, or TikTok video of the character speaking clearly.

Look for interviews, speeches, or monologues where there is little to no background music.
Grab the URL of the best candidate video.

使用你的网页搜索能力，找到YouTube、Bilibili或TikTok上该角色清晰发言的视频。

优先选择几乎没有背景音乐的采访、演讲或独白内容。
获取最合适的候选视频的URL。

3. Download Video and Subtitles

3. 下载视频和字幕

Use the

youtube-downloader

skill to download the video and its auto-generated subtitles. Wait for the download to complete before proceeding.

bash

undefined

使用

youtube-downloader

skill下载视频及其自动生成的字幕。等待下载完成后再进行后续操作。

bash

undefined

Example using youtube-downloader

Example using youtube-downloader

python skills/youtube-downloader/scripts/download_video.py "VIDEO_URL" -o "tmp/character_audio" --audio-only --subtitles

undefined

python skills/youtube-downloader/scripts/download_video.py "VIDEO_URL" -o "tmp/character_audio" --audio-only --subtitles

undefined

4. Extract Audio Segment

4. 提取音频片段

Read the downloaded subtitle file (e.g.,

.vtt

or

.srt

) to find a continuous 10-30 second segment where the character is speaking clearly without long pauses. Note the start and end timestamps.

Use

ffmpeg

to extract this specific audio segment as a

.wav

file to use as the reference audio.

bash

undefined

读取下载的字幕文件（例如

.vtt

或

.srt

格式），找到一段10-30秒的连续片段，要求角色发言清晰、无长时间停顿。记下起止时间戳。

使用

ffmpeg

将该特定音频片段提取为

.wav

文件，用作参考音频。

bash

undefined

Example: Extracting audio from 00:01:15 to 00:01:30

Example: Extracting audio from 00:01:15 to 00:01:30

ffmpeg -y -i "tmp/character_audio/VideoTitle.m4a" -ss 00:01:15 -to 00:01:30 -c:a pcm_s16le -ar 24000 -ac 1 "skills/chat-with-anyone/character_name_ref.wav"

undefined

ffmpeg -y -i "tmp/character_audio/VideoTitle.m4a" -ss 00:01:15 -to 00:01:30 -c:a pcm_s16le -ar 24000 -ac 1 "skills/chat-with-anyone/character_name_ref.wav"

undefined

5. Generate Speech and Roleplay

5. 生成语音并角色扮演

Respond to the user's prompt while staying in character. Use the

tts

skill with the extracted audio as

--ref-audio

to generate the spoken response.

bash

undefined

保持角色设定回应用户的prompt。使用

tts

skill，将提取的音频作为

--ref-audio

参数生成语音回复。

bash

undefined

Example using tts skill

Example using tts skill

bash skills/tts/scripts/tts.sh speak -t "Hello there! I am ready to chat with you." --ref-audio "skills/character-chat/character_name_ref.wav" -o "output.wav"

undefined

bash skills/tts/scripts/tts.sh speak -t "Hello there! I am ready to chat with you." --ref-audio "skills/character-chat/character_name_ref.wav" -o "output.wav"

undefined

Example Conversation

对话示例

User: 我想跟特朗普聊天，让他给我讲个睡前故事。

Agent:

(Internal) Identify character: Donald Trump.
(Internal) Find a good speech video URL:
```
https://www.youtube.com/watch?v=xxxxxxxx
```
.

(Internal) Download audio & subs:

python skills/youtube-downloader/scripts/download_video.py "https://www.youtube.com/watch?v=xxxxxxxx" -o tmp/trump --audio-only --subtitles

(Internal) Read subtitle, find good segment (e.g. 00:02:10 to 00:02:30).

(Internal) Extract clean wav:

ffmpeg -y -i "tmp/trump/audio.m4a" -ss 00:02:10 -to 00:02:30 -c:a pcm_s16le "skills/chat-with-anyone/trump_ref.wav"

(Internal) Generate TTS:

bash skills/tts/scripts/tts.sh speak -t "Let me tell you a tremendous story, maybe the best story ever told..." --ref-audio "skills/chat-with-anyone/trump_ref.wav" -o "trump_story.wav"

Agent replies: "Here is the audio of the bedtime story from Donald Trump!" (Presents
```
trump_story.wav
```
and the text).

User: 我想跟特朗普聊天，让他给我讲个睡前故事。

Agent:

(内部操作) 识别角色: Donald Trump。
(内部操作) 找到合适的演讲视频URL:
```
https://www.youtube.com/watch?v=xxxxxxxx
```
。

(内部操作) 下载音频和字幕:

python skills/youtube-downloader/scripts/download_video.py "https://www.youtube.com/watch?v=xxxxxxxx" -o tmp/trump --audio-only --subtitles

(内部操作) 读取字幕，找到合适的片段（例如00:02:10到00:02:30）。

(内部操作) 提取干净的wav文件:

ffmpeg -y -i "tmp/trump/audio.m4a" -ss 00:02:10 -to 00:02:30 -c:a pcm_s16le "skills/chat-with-anyone/trump_ref.wav"

(内部操作) 生成TTS:

bash skills/tts/scripts/tts.sh speak -t "Let me tell you a tremendous story, maybe the best story ever told..." --ref-audio "skills/chat-with-anyone/trump_ref.wav" -o "trump_story.wav"

Agent回复: "这是唐纳德·特朗普讲的睡前故事音频！"（展示
```
trump_story.wav
```
文件和对应文本）。

Dependencies

依赖项

youtube-downloader: For fetching videos and subtitles.
ffmpeg: For trimming and converting audio formats.
tts: For generating the final speech using
```
--ref-audio
```
(typically requires Noiz backend for voice cloning).

youtube-downloader: 用于获取视频和字幕。
ffmpeg: 用于裁剪和转换音频格式。
tts: 用于使用
```
--ref-audio
```
参数生成最终语音（通常需要Noiz后端支持语音克隆）。