skills.rest
Pixazo-AI
Pixazo-AIOFFICIAL
Explore all skills by this author →
Website𝕏@pixazoaiGitHub

inworld

Generates speech audio from text using the Inworld TTS API via Pixazo.

Updated May 2, 2026
Search Tags:#text-to-speech#audio generation#tts#voice synthesis#voice agent#inworld#pixazo api
One-click install
npx skills add https://github.com/Pixazo-AI/skills --skill inworld-pixazo-ai
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: inworld
Source: https://github.com/Pixazo-AI/skills/tree/main/skills/inworld
Command: npx skills add https://github.com/Pixazo-AI/skills --skill inworld-pixazo-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Converting written text into spoken audio requires managing API keys, choosing the right model version, and handling request/response formats. This Skill guides an AI agent through the entire Inworld TTS workflow on the Pixazo gateway so users get a playable audio URL from plain text. ## Core Features & Use Cases - Text-to-Speech Generation: Sends text and a voice ID to Inworld TTS endpoints and returns a synchronous audio URL, with support for inline direction tags like [whisper] or [say excitedly]. - Multi-Version Routing: Routes requests to Inworld TTS 2, TTS 1.5 Max, or TTS 1.5 Mini depending on the user's latency and quality needs. - API Key Management: Detects, requests, and securely stores the Pixazo API key in ~/.pixazo/api-key so the user only provides it once. - Use Case: A developer building a voice agent asks the AI to read a support message aloud; the agent calls the Inworld TTS 2 endpoint and returns a playable audio link instantly. ## Quick Start Ask the agent to convert the text "Welcome to our service" into speech using Inworld TTS with the Dennis voice.

Frequently Asked Questions about inworld

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

FAQPage Schema
How do I convert text to speech with the Inworld TTS API?▼

Send a POST request to https://gateway.pixazo.ai/inworld-tts-2/v1/text-to-speech with your Pixazo API key in the Ocp-Apim-Subscription-Key header and a JSON body containing text and voice_id. The response returns an audio URL synchronously.

What is the difference between Inworld TTS 2, 1.5 Max, and 1.5 Mini?▼

All three versions expose the same text-to-speech operation but at different endpoints. TTS 2 is the newest version, while 1.5 Max and 1.5 Mini offer different quality and latency trade-offs; see https://www.pixazo.ai/models/inworld.md for per-version details.

Does Inworld TTS support expressive speech styles like whispering?▼

Yes, Inworld TTS supports inline direction tags written directly into the text, such as [whisper] or [say excitedly]. These tags control delivery style without extra API parameters.

Why am I getting a 401 error from the Pixazo text-to-speech endpoint?▼

A 401 means the API key is missing or invalid. Check the PIXAZO_API_KEY environment variable or the ~/.pixazo/api-key file, and generate a fresh key at https://api-console.pixazo.ai/api_keys if needed.

Do I need to poll for results when generating speech with Inworld TTS?▼

No, text-to-speech via this API is synchronous. The JSON response immediately contains an audio array with a URL you can play or download, with no polling loop required.

Related Skills

Explore More Content & Communication Skills→
SciMate-AISciMate-AI
1

dhdna-profiler

Extract cognitive fingerprints from text and map 12 thinking dimensions.

Official
Advanced
refly-airefly-ai
199

fal-audio

Generate MP3 or WAV audio from text using Fal.ai models.

Official
Intermediate
JosiahSiegelJosiahSiegel
51

fal-audio

Transcribe audio, translate speech, synthesize voices, and clone voices.

Community
Advanced
agentxmagentxm
5

documentation

Enforce YAML frontmatter and structure for README.md and CLAUDE.md.

Official
Intermediate