skills.rest
vm0-ai
vm0-aiOFFICIAL
Explore all skills by this author →
WebsiteGitHub

elevenlabs

Convert text to speech using ElevenLabs voices and v1 endpoints.

76|18|Updated Dec 12, 2025
Search Tags:#text-to-speech#audio#elevenlabs#tts#curl
One-click install
npx skills add https://github.com/vm0-ai/vm0-skills --skill elevenlabs
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: elevenlabs
Source: https://github.com/vm0-ai/vm0-skills/tree/main/elevenlabs
Command: npx skills add https://github.com/vm0-ai/vm0-skills --skill elevenlabs

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Generate natural-sounding speech from text using ElevenLabs' AI voices without building a custom SDK.

Core Features & Use Cases

  • Text-to-speech: Convert text into speech using multiple voices.
  • Voice discovery: List available voices and models.
  • Streaming: Real-time audio streaming for responsive apps.

Quick Start

With ELEVENLABS_API_KEY set, curl a sample text-to-speech request and save the output to an MP3 file.

Frequently Asked Questions about elevenlabs

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I convert text to speech with realistic voices using curl?▼

Text-to-speech with realistic voices is generated by sending text to ElevenLabs' v1 endpoints via curl with your API key in the xi-api-key header. The service returns audio streams you can save directly to MP3 files for immediate playback or further processing.

What voices and models does ElevenLabs offer for TTS?▼

ElevenLabs provides multiple pre-built voices and models accessible via the v1 voices and models endpoints. You can list available options with curl to discover which voices suit your language, tone, and use case before generating speech.

Can I stream audio in real-time from text-to-speech without waiting for the full file?▼

Yes, ElevenLabs' streaming endpoints deliver audio in real-time chunks, enabling responsive applications like interactive dashboards and live voeovers that play audio as it's generated rather than after completion.

Do I need to build an SDK, or can I use text-to-speech with just HTTP requests?▼

You can use text-to-speech with standard curl HTTP requests to ElevenLabs' v1 endpoints without building or installing a custom SDK. Only an ELEVENLABS_API_KEY environment variable and proper headers are required.

What file formats and languages does ElevenLabs text-to-speech support?▼

ElevenLabs generates MP3 audio output and supports multiple languages through its voice models. The v1 endpoints handle language detection and voice selection, enabling voiceovers and narrations across diverse content types globally.

What setup is required before making text-to-speech requests?▼

Set the ELEVENLABS_API_KEY environment variable with your API credentials. With that single prerequisite, you're ready to call v1 endpoints via curl to list voices, models, and generate speech streams immediately.

Related Skills

Explore More Content & Communication Skills→
calesthiocalesthio
46.2k

setup-api-key

Validate ElevenLabs API keys and write them to a .env file.

Community
Intermediate
KaiserWhoLearnsKaiserWhoLearns

FFmpeg Format Conversion

Convert media files between containers and codecs using FFmpeg.

Community
Intermediate
tsuji-tomonoritsuji-tomonori

a11y-media-alternatives

Generate accessibility checklists for WCAG 2.2 multimedia compliance.

Community
Intermediate
malue-aimalue-ai
36

kokoro-tts

Generate local text-to-speech audio with Kokoro TTS engine.

Official
Intermediate