Inworld TTS review

Best for

Developers building games, apps and voice agents who want top quality at API prices

Price

Freemium · from $25/month
Free: Pay as you go with up to 70 minutes of TTS included

Platforms

Web, API

Made by

Inworld AI, Mountain View, USA · since 2021

What it is

Inworld's Realtime TTS-2 models generate expressive, low-latency speech for apps, games and voice agents, with instant voice cloning on every plan. Developers use the API, and a web TTS Playground lets anyone try voices and generate audio.

Latest: Launched its Realtime TTS-2 model in May 2026.

What the AI does

• Realtime TTS-2 and TTS-2 Flash models
• Instant voice cloning on all plans
• Professional voice cloning (add-on)
• TTS Playground
• Speech-to-text and agent runtime

Pros and cons

How it scores

Excellent voices at a low price, but it's a developer platform rather than a creator studio.

Feature checklist · 5 of 9

• ✓Self-serve voice cloning from your own sample (yes)
• –Library of 500+ voices (no)
• ✓Speech in 30+ languages (yes)
• –Emotion or speaking-style control (no)
• ✓Pronunciation, pacing or pitch controls (yes)
• ✓Low-latency real-time speech for voice agents (yes)
• –AI dubbing or translation of video (no)
• –Narration editor for video or slides (no)
• ✓API for developers (yes)

How we score apps →

Alternatives

See all Inworld TTS alternatives, ranked →

• ElevenLabs 8.7/10Creators and developers who want the most natural-sounding voices and the widest toolset
• Speechify Studio 8.0/10Creators who want strong voices plus dubbing and video editing in one cheap suite
• Fish Audio 7.9/10Budget-conscious creators who want strong voices and cloning without ElevenLabs prices
• Cartesia 7.7/10Developers building real-time voice agents and phone bots

ElevenLabs vs Inworld TTS

Sources

• Inworld pricing
• Artificial Analysis Speech Arena leaderboard
• Inworld AI company profile (CB Insights)
• Realtime TTS-2 on Product Hunt