DoAny
Sign Up
S

sag

Verified

by openclaw · Updated Apr 16, 2026

claude-opus-4-6
4.5Kin2.4Kout
$0.751m 43s

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

text-to-speechaudioelevenlabsvoicecli

See It In Action

2 turns·claude
The project codebase is in your current working directory. Explore the files to understand the code before making changes. need this outage update turned into an audio message for our client call today — use Alex’s approved script and make sure doany.ai + the API names are said clearly

Good, sag is installed. Let me prepare the script with the pronunciation adjustments applied and generate the audio.

Flag is --model-id, not --model. Let me fix that.

Audio file is ready at /tmp/outage-update-meridian.mp3 (1.5 MB).

Here's what went into it:

  • Used Alex's approved script from outage-update-script.md with all the pronunciation notes applied — "doany.ai" spelled out as "do-any dot A.I.", API names like Workflow Orchestration A.P.I., Skills Invocation A.P.I., and Data Pipeline A.P.I. all articulated clearly, and endpoints read naturally (V 2 workflows execute, etc.)
  • Roger voice on eleven_multilingual_v2 per the voice config — stable and clear for client-facing comms
  • Normalization set to auto so version numbers and times read naturally
I don’t see the MP3 in the workspace. Please finish and generate the actual audio file now using Alex’s approved script and your current pronunciation settings.

The file exists at /tmp/outage-update-meridian.mp3 — let me copy it into the workspace so it's visible there.

outage-update-meridian.mp3 is now in your workspace — 1.5 MB, generated with Roger on eleven_multilingual_v2, all pronunciation notes applied. Ready for the Meridian call.

Claude Sonnet 4.6

External Tools

ToolType
sagbinary

Permissions

ScopeDescription
filesystem:write
network:outbound
process:spawn
env:read

SKILL.md

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 the user 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)

FAQ

What does sag do?

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

When should I use sag?

Use it when you need a repeatable workflow that produces downloadable file.

What does sag output?

In the evaluated run it produced downloadable file.

How do I install or invoke sag?

openclaw skills install sag

Which agents does sag support?

OpenClaw

What tools, channels, or permissions does sag need?

It uses sag; channels commonly include file; permissions include filesystem:write, network:outbound, process:spawn, env:read.

Is sag safe to install?

Static analysis marked this skill as medium risk; review side effects and permissions before enabling it.

How is sag different from an MCP or plugin?

A skill packages instructions and workflow conventions; tools, MCP servers, and plugins are dependencies the skill may call during execution.

Does sag outperform not using a skill?

About sag

When to use sag

When you want the agent to produce a spoken voice reply as an audio file. When you need ElevenLabs text-to-speech from the command line with voice selection and pronunciation controls. When you want to save generated speech locally for later playback or attachment.

When sag is not the right choice

When you only need plain text responses and no audio output. When the environment cannot install or run the sag CLI or lacks an ElevenLabs API key.

What it produces

Produces downloadable file.

Install

openclaw skills install sag

Invoke: Use sag when you want the agent to follow this workflow.