skills.rest
Aadi-110i
Aadi-110iCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

text-to-speech

Convert text to natural speech using ElevenLabs, Kokoro, and other TTS models via the inference.sh CLI.

Updated Jul 28, 2026
Search Tags:#text-to-speech#podcast#elevenlabs#tts#voiceover#voice generation#kokoro
One-click install
npx skills add https://github.com/Aadi-110i/PEP-PROJECT --skill text-to-speech-aadi-110i
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: text-to-speech
Source: https://github.com/Aadi-110i/PEP-PROJECT/tree/main/skills/text-to-speech
Command: npx skills add https://github.com/Aadi-110i/PEP-PROJECT --skill text-to-speech-aadi-110i

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Creating voiceovers, audiobooks, podcasts, or narration traditionally requires recording equipment, voice talent, and editing time. This Skill lets you generate natural-sounding speech from plain text using multiple AI voice models through a single CLI. ## Core Features & Use Cases - Multiple TTS Models: Choose from ElevenLabs (premium, 22+ voices, 32 languages), DIA TTS (conversational), Kokoro (fast), Chatterbox, Higgs Audio (emotional control), and VibeVoice (long-form podcasts). - Expressive & Multi-Speaker Speech: Generate conversational dialogue, emotional delivery, and podcast-length audio. - Video Pipeline Integration: Combine generated speech with talking-head avatar tools like OmniHuman for narrated videos. - Use Case: Write a product demo script, run it through Kokoro TTS to produce a voiceover, then feed the audio into an avatar video generator for a complete narrated presentation. ## Quick Start Ask the assistant to generate speech from your text using the Kokoro TTS model via the belt CLI, for example: convert 'Welcome to our tutorial' into an audio file.

Frequently Asked Questions about text-to-speech

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

FAQPage Schema
How do I convert text to speech with the inference.sh CLI?▼

Run belt app run with a TTS app ID and a JSON input containing your text, for example belt app run infsh/kokoro-tts with an input of {"text": "Hello"}. You must first install the belt CLI and authenticate with belt login.

Which text-to-speech model should I use for podcasts?▼

VibeVoice (infsh/vibevoice) is designed for long-form podcast audio. For shorter conversational content, DIA TTS works well, while ElevenLabs offers premium quality with 22+ voices across 32 languages.

ElevenLabs vs Kokoro TTS, what is the difference?▼

ElevenLabs TTS provides premium voice quality with over 22 voices and 32 language support. Kokoro TTS is optimized for fast, natural-sounding generation, making it better for quick iterations and simple narration tasks.

Can I control emotion in AI-generated speech?▼

Yes, Higgs Audio (infsh/higgs-audio) supports emotional control through an emotion parameter in the input JSON, such as setting emotion to excited. DIA TTS also produces expressive conversational delivery.

How do I combine generated speech with a talking avatar video?▼

Generate speech first with a TTS app like Kokoro, then pass the resulting audio URL to bytedance/omnihuman-1-5 along with a portrait image URL. The avatar video tool lip-syncs the image to your audio.

Related Skills

Explore More Content & Communication Skills→
TheTesseractAITheTesseractAI

podcast-generator

Convert research or articles into podcast scripts and audio via ElevenLabs text-to-speech.

Community
Intermediate
inference-shinference-sh
688

ai-avatar-video

Generates AI avatar and talking head videos via the inference.sh CLI.

Official
Intermediate
inference-shinference-sh
688

ai-podcast-creation

Generate podcasts by synthesizing text-to-speech audio, composing music, and merging audio elements.

Official
Intermediate
damionrashforddamionrashford
15

media-tts-ai

Synthesize audio from text using open-source TTS models.

Community
Advanced