Submit projectSubmit

Inworld AI

inworld.ai

A realtime voice API with Realtime TTS-2 text-to-speech, streaming speech-to-text and speech-to-speech, plus hosted open-model LLM inference, aimed at consumer apps.

Speech & Transcription

Save privately. Follow for reviewed updates in your SOTA inbox. Neither changes the ranking.

Your workspace

About Inworld AI

Consumer voice apps such as companions, tutors and coaches need natural speech with low latency at a per-user cost that stays affordable at scale.

Who it’s for

  • Developers building voice companions, tutors and other consumer voice apps
  • Teams adding expressive, low-latency text-to-speech to a voice agent stack such as LiveKit Agents

When to consider it

Consider Inworld AI when you want realtime text-to-speech, speech-to-text and LLM inference billed from one credit balance, with voice cloning and voice design included on the free tier.

Tradeoffs & limitations

  • The free On-Demand tier is pay as you go and includes up to 70 minutes of TTS; usage is billed at $25 per 1M characters for Realtime TTS-2 and $15 per 1M characters for Realtime TTS-2 Flash.
  • Paid plans start at $25 a month (Creator), with credits equal to the plan price; HIPAA/BAA and zero data retention are add-ons from the $1,500-a-month Growth plan, and EU or India data residency is Enterprise only.

SOTA overview · Documentation-based assessment · Sources & review method

Updates

No updates shared yet.

Discussion

Newest first

Ask a question or share how you use Inworld AI.

Keep it helpful. Community rules

Loading discussion…

Sources & review method

Documentation-based assessment · Nov 1, 2026 · Prepared with AI assistance; not a hands-on benchmark.

Checked by SOTA · AI-assisted documentation review. Selection advice is our assessment; verify current requirements for your deployment.

Editorial policy · Suggest a correction

Import history & original evidence

Inworld AI official website

Scope: Product overview · Imported Nov 1, 2026

A realtime voice API with Realtime TTS-2 text-to-speech, streaming speech-to-text and speech-to-speech, plus hosted open-model LLM inference, aimed at consumer apps.

Based on official pages and announcements checked on 2026-11-01. No hands-on test, performance benchmark or popularity ranking is claimed.