skills.rest
zamansepeti43
zamansepeti43COMMUNITY
Explore all skills by this author →
GitHub

elevenlabs

Generate voiceovers, sound effects, and music using ElevenLabs APIs.

Updated Sep 1, 2026
Search Tags:#text-to-speech#sound effects#music generation#elevenlabs#voice cloning#voiceover#remotion
One-click install
npx skills add https://github.com/zamansepeti43/c-rak-agent --skill elevenlabs-zamansepeti43
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: elevenlabs
Source: https://github.com/zamansepeti43/c-rak-agent/tree/main/video-engine/.agents/skills/elevenlabs
Command: npx skills add https://github.com/zamansepeti43/c-rak-agent --skill elevenlabs-zamansepeti43

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires elevenlabs, and includes references (resource) components.

What problem does it solve? Producing narration, sound effects, and background music for videos, podcasts, or games normally requires voice actors, recording equipment, and audio licensing. This Skill generates all of that audio programmatically through the ElevenLabs API, including synchronization with Remotion video compositions. ## Core Features & Use Cases - Text-to-Speech: Generate voiceovers with model selection (multilingual_v2, flash, turbo, v3), voice settings presets, SSML pause and pronunciation control, and voice cloning from audio samples. - Sound Effects & Music: Create sound effects up to 22 seconds from text descriptions and instrumental music from 10 seconds to 5 minutes with genre, mood, and instrument prompts. - Remotion Integration: Sync generated audio to video scenes using manifest.json durations, per-scene audio components, fade/delay patterns, and demo-video playback rate matching. - Use Case: Write a VOICEOVER-SCRIPT.md for a product demo video, generate per-scene narration MP3s with a timing manifest, then bind them to Remotion Series sequences so visuals automatically match voiceover length. ## Quick Start Generate a professional voiceover MP3 from my narration script using the ElevenLabs multilingual model and save it for my video project.

Frequently Asked Questions about elevenlabs

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

FAQPage Schema
How do I generate a voiceover with the ElevenLabs API in Python?▼

Create an ElevenLabs client with your API key and call client.text_to_speech.convert with text, a voice_id, and a model_id like eleven_multilingual_v2. Save the returned audio stream with the save() helper to produce an MP3 file.

Which ElevenLabs TTS model should I use for narration?▼

Use eleven_multilingual_v2 for stable, production-ready narration across 29 languages. Choose eleven_flash_v2_5 or eleven_turbo_v2_5 when you need SSML break and phoneme tags or low latency, and eleven_v3 only for maximum expressiveness with expected retakes.

How do I add pauses between sentences in ElevenLabs TTS?▼

With flash or turbo models, insert SSML break tags like <break time="1.5s" /> inline, up to 3 seconds each. Multilingual_v2 and v3 lack SSML support, so use blank-line paragraph breaks or insert silence afterward with ffmpeg. Ellipsis is not a reliable pause.

Can I clone my own voice with ElevenLabs?▼

Yes, use client.voices.ivc.create with one or more MP3 samples opened in binary mode for instant voice cloning. Professional Voice Cloning requires a Creator plan, at least 30 minutes of audio, and a verification recording before training.

How do I sync ElevenLabs audio with Remotion video scenes?▼

Generate per-scene MP3s with a manifest.json containing durations, convert seconds to frames with Math.ceil(duration * fps), and set each Series.Sequence durationInFrames accordingly. Add Audio components per scene or one continuous track across the composition.

What are the limits of ElevenLabs sound effect and music generation?▼

Sound effects are capped at 22 seconds per generation, and music ranges from 10 seconds to 5 minutes. Concurrent generation limits depend on your tier, from 2 concurrent TTS requests on Free up to 15 on Scale.

Related Skills

Explore More Content & Communication Skills→
microsoftmicrosoft
1.4k

tts-voiceover

Generates per-slide WAV voice-overs from YAML speaker notes using Azure Speech SDK.

Official
Advanced
GoooIceGoooIce

remotion-video

Automates MP4 video creation from React components using Remotion and synchronized TTS audio workflows.

Community
Advanced
chuanyue98chuanyue98

space-video-audio

Generates TTS voiceovers, sources royalty-free BGM, and mixes audio into videos with ffmpeg.

Community
Intermediate
zhongjjm-designzhongjjm-design

mimo-voiceclone

Generate WAV speech audio from text using a cloned voice via the MiMo VoiceClone API.

Community
Intermediate