Agent-Skills.md

Agent Skills: Inworld AI

Inworld TTS API. Covers voice cloning, audio markups, timestamps. Keywords: text-to-speech, visemes.

UncategorizedID: itechmeat/llm-code/inworld

Repository

itechmeat/llm-code
itechmeatLicense: MIT
2

Install this agent skill to your local

pnpm dlx add-skill https://github.com/itechmeat/llm-code/tree/HEAD/skills/inworld

Skill Files

Browse the full folder contents for inworld.

Download Skill

Loading file tree…

skills/inworld/SKILL.md

Skill Metadata

Name
inworld
Description
"Inworld TTS API. Covers voice cloning, audio markups, timestamps. Keywords: text-to-speech, visemes."

Inworld AI

Text-to-Speech platform with voice cloning, audio markups, and timestamp alignment.

Quick Navigation

| Topic | Reference | | ------------- | ----------------------------------------------- | | Installation | installation.md | | Voice Cloning | cloning.md | | Voice Control | voice-control.md | | API Reference | api.md |

When to Use

  • Text-to-speech audio generation
  • Voice cloning from 5-15 seconds of audio
  • Emotion-controlled speech ([happy], [sad], etc.)
  • Word/phoneme timestamps for lip sync
  • Custom pronunciation with IPA

Models

| Model | ID | Latency | Price | | ------------ | ---------------------- | ------- | ------------ | | TTS 1.5 Max | inworld-tts-1.5-max | ~200ms | $10/1M chars | | TTS 1.5 Mini | inworld-tts-1.5-mini | ~120ms | $5/1M chars |

Minimal Example

import requests, base64, os

response = requests.post(
    "https://api.inworld.ai/tts/v1/voice",
    headers={"Authorization": f"Basic {os.getenv('INWORLD_API_KEY')}"},
    json={"text": "Hello!", "voiceId": "Ashley", "modelId": "inworld-tts-1.5-max"}
)
audio = base64.b64decode(response.json()['audioContent'])

Key Features

  • 15 languages — en, zh, ja, ko, ru, it, es, pt, fr, de, pl, nl, hi, he, ar
  • Instant cloning — 5-15 seconds audio, no training
  • Audio markups — [happy], [laughing], [sigh] (English only)
  • Timestamps — word, phoneme, viseme timing for lip sync
  • Streaming — /voice:stream endpoint

Prohibitions

  • Audio markups work only in English
  • Use ONE emotion markup at text beginning
  • Match voice language to text language
  • Instant cloning may not work for children's voices or unique accents

Links