sag

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

sag

Use

sag

for ElevenLabs TTS with local playback.

API key (required)

```
ELEVENLABS_API_KEY
```
(preferred)
```
SAG_API_KEY
```
also supported by the CLI

Quick start

```
sag "Hello there"
```
```
sag speak -v "Roger" "Hello"
```
```
sag voices
```
```
sag prompting
```
(model-specific tips)

Model notes

Default:
```
eleven_v3
```
(expressive)
Stable:
```
eleven_multilingual_v2
```
Fast:
```
eleven_flash_v2_5
```

Pronunciation + delivery rules

First fix: respell (e.g. "key-note"), add hyphens, adjust casing.
Numbers/units/URLs:
```
--normalize auto
```
(or
```
off
```
if it harms names).
Language bias:
```
--lang en|de|fr|...
```
to guide normalization.
v3: SSML
```
<break>
```
not supported; use
```
[pause]
```
,
```
[short pause]
```
,
```
[long pause]
```
.
v2/v2.5: SSML
```
<break time="1.5s" />
```
supported;
```
<phoneme>
```
not exposed in
```
sag
```
.

v3 audio tags (put at the entrance of a line)

```
[whispers]
```
,
```
[shouts]
```
,
```
[sings]
```

[laughs]

[starts laughing]

[sighs]

[exhales]

[sarcastic]

[curious]

[excited]

[crying]

[mischievously]

Example:

sag "[whispers] keep this quiet. [short pause] ok?"

Voice defaults

```
ELEVENLABS_VOICE_ID
```
or
```
SAG_VOICE_ID
```

Confirm voice + speaker before long output.

使用

sag

实现ElevenLabs文本转语音（TTS）的本地播放功能。

API密钥（必填）

```
ELEVENLABS_API_KEY
```
（推荐使用）
CLI也支持
```
SAG_API_KEY
```

快速开始

```
sag "Hello there"
```
```
sag speak -v "Roger" "Hello"
```
```
sag voices
```
```
sag prompting
```
（模型专属提示技巧）

模型说明

默认模型：
```
eleven_v3
```
（表现力强）
稳定模型：
```
eleven_multilingual_v2
```
快速模型：
```
eleven_flash_v2_5
```

发音与表达规则

首要修正方法：重新拼写（例如"key-note"）、添加连字符、调整大小写。
数字/单位/网址：使用
```
--normalize auto
```
（若对名称识别有影响则设为
```
off
```
）。
语言偏向：使用
```
--lang en|de|fr|...
```
引导标准化处理。
v3模型：不支持SSML
```
<break>
```
标签；请使用
```
[pause]
```
、
```
[short pause]
```
、
```
[long pause]
```
。
v2/v2.5模型：支持SSML
```
<break time="1.5s" />
```
标签；
```
sag
```
未开放
```
<phoneme>
```
标签的使用权限。

v3音频标签（置于行首）

```
[whispers]
```
、
```
[shouts]
```
、
```
[sings]
```

[laughs]

、

[starts laughing]

、

[sighs]

、

[exhales]

[sarcastic]

、

[curious]

、

[excited]

、

[crying]

、

[mischievously]

示例：

sag "[whispers] keep this quiet. [short pause] ok?"

默认语音设置

```
ELEVENLABS_VOICE_ID
```
或
```
SAG_VOICE_ID
```

在生成长篇输出前，请确认语音与发声者设置。

Chat voice responses

聊天语音回复

When Peter asks for a "voice" reply (e.g., "crazy scientist voice", "explain in voice"), generate audio and send it:

bash

undefined

当Peter要求以“语音”形式回复（例如“疯狂科学家语音”、“用语音解释”）时，生成音频并发送：

bash

undefined

Generate audio file

生成音频文件

sag -v Clawd -o /tmp/voice-reply.mp3 "Your message here"

Then include in reply:

然后在回复中包含：

MEDIA:/tmp/voice-reply.mp3


Voice character tips:

- Crazy scientist: Use `[excited]` tags, dramatic pauses `[short pause]`, vary intensity
- Calm: Use `[whispers]` or slower pacing
- Dramatic: Use `[sings]` or `[shouts]` sparingly

Default voice for Clawd: `lj2rcrvANS3gaWWnczSX` (or just `-v Clawd`)


语音角色技巧：

- 疯狂科学家：使用`[excited]`标签、戏剧性停顿`[short pause]`，调整语气强度
- 沉稳风格：使用`[whispers]`标签或放慢语速
- 戏剧风格：谨慎使用`[sings]`或`[shouts]`标签

Clawd的默认语音ID：`lj2rcrvANS3gaWWnczSX`（或直接使用`-v Clawd`）