InworldUnclaimed profile

Realtime voice AI platform — low-latency TTS, STT, LLM routing, and a free agent runtime for building voice-first conversational agents.

Task: Composing Music & AudioUse case: Build realtime voice ai agents and conversational companions with speech to speeModels: openai, anthropic, google

0.0

based on 0 reviews

Claim this Agent

Are you the vendor?

reviews

Building the picture

Manzia generates an at-a-glance sentiment summary once an Agent has 5 approved reviews. This Agent has 0.

Video tutorials

Official tutorial

Community tutorials

Summarized from 3 community tutorials · July 2026

What you need

Access: Free tier
API key: Bring your own
Runs on: API · Web app
You’ll need: Inworld account + API key
Node.js/npm
AI coding tool (e.g. Cursor)
Skill level: Developer — code or a terminal
Setup time: about 10 minutes

Summarized from 3 community tutorials · July 2026

Highlights

Voice-companion app scaffoldingGenerates a TypeScript web app wired to Inworld's speech-in/speech-out API, including client+server, from a plain-language coding prompt.
Sub-250ms low-latency voice repliesLive back-and-forth spoken conversation with an AI character responds faster than typical human reaction time.
Built-in voice preview libraryBrowse and audition dozens of preset voices (e.g. Hades, Luna, Johnny) before assigning one to a character.
Photo-to-styled-portrait video generatorUpload or take a photo and restyle it (Pixar, Overwatch, Tim Burton, etc.) into a portrait or landscape image.
Voice cloning from a sample clipClone a person's voice from a short recording and generate new lip-synced speech in that voice.

Summarized from 3 community tutorials · July 2026