sag

clawdbot's avatarfrom clawdbot

ElevenLabs text-to-speech with mac-style say UX.

⭐3.1kstars🔀474forks📁View on GitHub🕐Updated Jan 11, 2026
[Video and Script Planning]

When & Why to Use This Skill

This Claude skill integrates ElevenLabs' industry-leading Text-to-Speech (TTS) technology, providing a powerful 'say' command interface for generating high-quality, expressive audio. It supports multiple AI models—including the highly expressive v3 and the low-latency Flash v2.5—and allows for fine-grained control over emotional delivery using tags like [whispers], [shouts], or [excited]. Designed for seamless local playback and file generation, it is an essential tool for creators needing realistic voice synthesis.

Use Cases

  • Professional Voiceover Production: Automatically generate high-fidelity narrations for video scripts, advertisements, and presentations directly from Claude.
  • Expressive AI Personas: Create immersive storytelling or roleplay experiences by utilizing emotional tags and specific voice characters to match the narrative tone.
  • Accessibility & Multitasking: Convert long-form text or complex explanations into clear, natural-sounding speech for hands-free listening or to assist users with visual impairments.
  • Technical Pronunciation Tuning: Use normalization rules and language bias settings to ensure technical jargon, URLs, and foreign terms are pronounced accurately.
namesag
descriptionElevenLabs text-to-speech with mac-style say UX.
homepagehttps://sag.sh
metadata{"clawdbot":{"emoji":"🗣️","requires":{"bins":["sag"],"env":["ELEVENLABS_API_KEY"]},"primaryEnv":"ELEVENLABS_API_KEY","install":[{"id":"brew","kind":"brew","formula":"steipete/tap/sag","bins":["sag"],"label":"Install sag (brew)"}]}}

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.

Chat voice responses

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

# Generate 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 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)