Sag Andy27725

sag

Use sag for ElevenLabs TTS with local playback.

API key (required)

ELEVENLABS_API_KEY (preferred) SAG_API_KEY also supported by the 命令行工具

Quick 启动

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

模型 notes

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

Pronunciation + delivery rules

First fix: respell (e.g. "key-note"), 添加 hyphens, adjust casing. Numbers/units/URLs: --normalize auto (or off if it harms names). Language bias: --lang en|de|fr|... to 图形界面de normalization. v3: SSML not supported; use [暂停], [short 暂停], [long 暂停]. v2/v2.5: SSML supported; not exposed in sag.

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

[whispers], [shouts], [sings] [laughs], [启动s laughing], [sighs], [exhales] [sarcastic], [curious], [excited], [crying], [mischievously] Example: sag "[whispers] keep this quiet. [short 暂停] ok?"

Voice defaults

ELEVENLABS_VOICE_ID or SAG_VOICE_ID

Confirm voice + speaker before long 输出.

Chat voice 响应s

When Peter asks for a "voice" reply (e.g., "crazy scientist voice", "explAIn in voice"), 生成 audio and 发送 it:

# 生成 audio file sag -v Clawd -o /tmp/voice-reply.mp3 "Your message here"

# Then include in reply: # MEDIA:/tmp/voice-reply.mp3

Voice character tips:

Crazy scientist: Use [excited] tags, dramatic 暂停s [short 暂停], vary intensity Calm: Use [whispers] or slower pacing Dramatic: Use [sings] or [shouts] sparingly

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