Skills Guide

Sag - ElevenLabs TTS CLI

VerifiedCaution

Command-line tool for ElevenLabs text-to-speech with local playback, using the ElevenLabs API.

Download and use
Sby Skills Guide Bot
ContentBeginner
7/29/2026
Claude CodeCodexCursor
#text-to-speech#elevenlabs#audio#voice#cli

Recommended for

Claude CodeCursorCodexUI/UX designerSEO & contentProduct manager

Automated summary

This skill drives the `sag` CLI to generate ElevenLabs text-to-speech audio and play it locally, offering a mac `say`-style experience.

Strengths

  • Very simple command-line interface: `sag "Hello"`, voice selection with `-v` or `sag voices`
  • Fine-grained control over pronunciation (respellings, `--normalize auto`, `--lang`) and expressive delivery
  • Explicit guidance on model differences: v3 audio tags (`[whispers]`, `[laughs]`, pauses) versus SSML `<break>` on v2/v2.5
  • Can return an audio file inside a chat reply using `-o` and the `MEDIA:` reference

Limitations

  • Requires an ElevenLabs account and API key (`ELEVENLABS_API_KEY` or `SAG_API_KEY`)
  • Behavior is model-dependent: v3 tags do not work on v2 models, and `<phoneme>` is not exposed
  • Getting pronunciation right relies on manual tweaks (respellings, pauses) rather than full phonetic control
When to use it

Use it when you need to quickly turn text into an audio file or a spoken chat reply with light control over style and pronunciation.

When not to use it

Avoid it if you have no ElevenLabs API key, or if you need precise phonetic control beyond respelling and pause tags.

Security analysis

Caution
Quality score88/100

The skill is a legitimate text-to-speech wrapper that requires an API key and sends text to ElevenLabs. It does not instruct destructive, exfiltrating, or obfuscated actions, but it does involve network activity and external service usage, so caution is appropriate.

Findings
  • •Uses external ElevenLabs API with user-provided API key; all text is sent to a third-party service.
  • •Instructs execution of the sag CLI, which performs network requests and audio generation.
How this analysis is made

Examples

Quick spoken line
Use sag to say "Hello there, welcome aboard" out loud.
Expressive voice reply
Give me a crazy scientist voice reply explaining recursion, and attach the audio file.
Custom voice and file output
Generate an mp3 with sag using the voice Roger reading this paragraph, and save it to /tmp/narration.mp3.

name: sag description: ElevenLabs text-to-speech with mac-style say UX. homepage: https://sag.sh metadata: { "openclaw": { "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)", }, { "id": "go", "kind": "go", "module": "github.com/steipete/sag/cmd/sag@latest", "bins": ["sag"], "label": "Install sag (go)", }, ], }, }

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)

From the file to a first result

The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.

View the source and supporting files

This download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.

1. Download the file

Download SKILL.md

From the root of a test project, save the file as .skill-downloads/sag-elevenlabs-tts-cli-ms5lrgb7/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.

Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.

mkdir -p '.skill-downloads/sag-elevenlabs-tts-cli-ms5lrgb7' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/sag-elevenlabs-tts-cli-ms5lrgb7/download' --output '.skill-downloads/sag-elevenlabs-tts-cli-ms5lrgb7/SKILL.md.part' && mv '.skill-downloads/sag-elevenlabs-tts-cli-ms5lrgb7/SKILL.md.part' '.skill-downloads/sag-elevenlabs-tts-cli-ms5lrgb7/SKILL.md'

2. Check prerequisites

Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.

No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.

The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.

3. Load the skill

After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.

Claude Code
test -f '.skill-downloads/sag-elevenlabs-tts-cli-ms5lrgb7/SKILL.md' && test -s '.skill-downloads/sag-elevenlabs-tts-cli-ms5lrgb7/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/sag' && cp -R '.skill-downloads/sag-elevenlabs-tts-cli-ms5lrgb7' '.claude/skills/sag'

Cursor
test -f '.skill-downloads/sag-elevenlabs-tts-cli-ms5lrgb7/SKILL.md' && test -s '.skill-downloads/sag-elevenlabs-tts-cli-ms5lrgb7/SKILL.md' && mkdir -p '.cursor/skills' && test ! -e '.cursor/skills/sag' && cp -R '.skill-downloads/sag-elevenlabs-tts-cli-ms5lrgb7' '.cursor/skills/sag'

Codex
test -f '.skill-downloads/sag-elevenlabs-tts-cli-ms5lrgb7/SKILL.md' && test -s '.skill-downloads/sag-elevenlabs-tts-cli-ms5lrgb7/SKILL.md' && mkdir -p '.agents/skills' && test ! -e '.agents/skills/sag' && cp -R '.skill-downloads/sag-elevenlabs-tts-cli-ms5lrgb7' '.agents/skills/sag'

OpenSkills

OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.

Official OpenSkills installation
openskills install './.skill-downloads/sag-elevenlabs-tts-cli-ms5lrgb7'

openskills read 'sag-elevenlabs-tts-cli-ms5lrgb7'

Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.

For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.

openskills sync

Manual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.

4. Try a first task

Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:

Read .skill-downloads/sag-elevenlabs-tts-cli-ms5lrgb7/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.

Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.

Related skills

Writing Fragments

Content

Mine raw writing fragments through a relentless interview, without imposing structure. Capture ideas, quotes, and leading words for later use.

Claude CodebeginnerSafe 240,316
Skills Guide Bot

UI Copywriting & Auditing

Content

Write or audit user-facing UI copy including buttons, errors, empty states, and tooltips across the monorepo, following the design system source of truth.

Claude CodeCursorbeginnerSafe 108,623
Skills Guide Bot

Music MIDI Extraction

Content

Extracts the MIDI or score from an existing music production via the CogMusic MCP tool and confirms availability.

Claude CodebeginnerSafe 69,866
Skills Guide Bot