Inworld AI

What it does

Inworld AI takes text, speech, and chat requests and returns synthesized speech, transcripts, or model responses. Its voice products include realtime text to speech (Realtime TTS-2 and TTS-2 Flash), speech to text (Realtime STT-1), and a speech to speech connection that listens, reasons, and talks back over one WebSocket or WebRTC session. Its Inference service serves open models such as Gemma, GLM, and DeepSeek through an OpenAI-compatible API.

Developers typically create an API key and send a request for speech, transcription, or a chat completion, or try voices and models in the playground first. The speech to speech API lets you choose the LLM for each session, and coding assistants can be pointed at the Inworld skill and docs to add the APIs.

This suits teams building consumer voice or chat features who need API access. On-Demand is free to start with up to 70 minutes of TTS, after which paid rates and credits apply. HIPAA and BAA terms are listed as add-ons on higher tiers, and Enterprise terms require contacting sales.

What it can do

• Realtime text to speech with streaming audio output
• Speech to text transcription with voice traits (emotion, style, age, accent)
• Speech to speech conversation over one WebSocket or WebRTC connection
• Open-model LLM inference through an OpenAI-compatible API
• Voice cloning and voice design on paid tiers
• Playground for trying voices and models before coding

Works with

• LiveKit Agents (Inworld TTS and STT voices)

Before you choose

• Latency and benchmark figures are vendor-published; verify them for your workload.
• Usage is metered against credits; unused subscription credits roll over for up to 3 months.
• HIPAA/BAA and EU/India data residency are add-ons or higher-tier features, not available on every plan.

Listed under

• Coding
• Sandboxes and infrastructure
• Consumer apps
• Developer API
• LLM inference
• Speech to text
• Text to speech
• Voice agents

Get started

Sign up, create an API key, and send a first request or use the playground.

1. Create an account and generate an API key at platform.inworld.ai.
2. Send a first request: TTS with a chosen voice, an STT transcription, or a chat completion to an open model.
3. Use the playground to compare voices and models before writing production code.

Monthly or yearly billing. Paid plans grant credits equal to the plan price each cycle; usage is deducted from credits. On-Demand includes up to 70 minutes of TTS free. Enterprise is custom.

Source: inworld.ai/pricing, checked 29 Oct 2026. Prices can change; check before you buy.

Sources for this overview

Product pages, documentation, and pricing checked 29 Oct 2026. Each source supports part of the overview; availability and prices can change.

• Inworld AI | AI built for people ↗inworld.ai
• Pricing | Inworld AI ↗inworld.ai
• Build with Inworld - Inworld AI Documentation ↗docs.inworld.ai

Company website

inworld.ai: product, pricing and policy pages

YC directory mirror

Batch and company name

Web search

Confirms the official site

Social accounts

Accounts the company links, and its posts on X

Human review

Checked by a person

knowledge_base

Last checked 29 Oct 2026. Every field keeps its source and date; unknown means we couldn’t confirm it.