elevenlabs-pro

ElevenLabs advanced TTS for converting text to speech, listing voices, and managing credits

Safety Notice

This listing is from the official public ClawHub registry. Review SKILL.md and referenced scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "elevenlabs-pro" with this command: npx skills add Jack2/openclaw-skill-elevenlabs-pro

ElevenLabs Pro Skill

Advanced text-to-speech using the ElevenLabs API. Supports voice selection, language/gender filtering, audio file generation, and credit tracking.

Prerequisites

Set your API key as an environment variable:

export ELEVENLABS_API_KEY=sk_...

Or pass it directly with --api-key.

Usage

Convert text to speech

python3 scripts/elevenlabs.py "Hello world" --voice Sarah --output audio.mp3

List available voices

python3 scripts/elevenlabs.py --list-voices
python3 scripts/elevenlabs.py --list-voices --lang en --gender female
python3 scripts/elevenlabs.py --list-voices --json

Check remaining credits

python3 scripts/elevenlabs.py --credits

Options

OptionDefaultDescription
--voice NAMERachelVoice name (partial match supported)
--voice-id IDDirect voice ID (overrides --voice)
--output PATHoutput.mp3Output MP3 file path
--model IDeleven_turbo_v2_5Model ID
--stability0.5Voice stability (0–1)
--similarity0.75Similarity boost (0–1)
--style0.0Style exaggeration (0–1)
--lang CODEFilter voices by language (e.g. en, fr)
--genderFilter voices by gender (male/female)
--jsonOutput as JSON
--api-key KEYAPI key (overrides env var)

Available Models

Model IDDescription
eleven_turbo_v2_5Fastest, lowest latency (free tier supported)
eleven_multilingual_v2Best quality, multilingual
eleven_flash_v2_5Ultra-low latency

Importable API

import sys
sys.path.insert(0, "path/to/skills/elevenlabs-pro/scripts")
from elevenlabs import list_voices, get_voice_id, text_to_speech, get_credits

api_key = "sk_..."
# TTS
voice_id = get_voice_id(api_key, "Sarah")
path = text_to_speech(api_key, "Hello!", voice_id, "out.mp3")

# Credits
info = get_credits(api_key)
print(info["characters_remaining"])

References

See references/voices.md for popular voices and voice parameter guidance.

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

General

Elevenlabs Tts

ElevenLabs TTS (Text-to-Speech) with emotional audio tags for expressive voice synthesis. WhatsApp-compatible voice messages with Opus conversion. Supports 7...

Registry SourceRecently Updated
65K
Profile unavailable
General

Feishu Voice Loop

Accept text or voice input, transcribe if needed, generate natural OpenAI TTS speech, and send audio output to Feishu chat or web player.

Registry SourceRecently Updated
0115
Profile unavailable
General

TTS AutoPlay with Wake Word

Auto-play TTS voice files with wake word detection. Only plays audio when user message contains wake words like "语音", "念出来", "voice", etc. Perfect for Webcha...

Registry SourceRecently Updated
0202
Profile unavailable