Inworld TTS logo

Inworld TTS

Low-latency & low-cost real-time text-to-speech API for voice agents and consumer apps, with speech-to-text and an LLM router on the same API.

Last verified: October 24, 2026
Alternative to: ElevenLabs
Inworld TTS app screenshot

Short description

Inworld TTS is a text-to-speech API that developers use to give apps and voice agents a voice. Inworld started out making AI characters for video games and now sells voice infrastructure, describing itself as infrastructure for production voice AI. It is API-only, with no studio or editor. Its pitch is ElevenLabs-like voice quality for apps, agents and companions at a fraction of the per-character price.

Features

  • Realtime TTS-2 (inworld-tts-2): Flagship model with a vendor-stated ~100ms time to first audio for 90% of requests, plus control over delivery, pauses and pronunciation, and timestamps with phonemes and visemes (mouth shapes) for lip-syncing avatars

  • TTS-2 Flash (inworld-tts-2-flash): Cheapest and fastest model, with a vendor-stated ~20ms server-side response time, and as low as 50ms on the Coval benchmark per the vendor. It drops professional cloning and delivery control.

  • Instant voice cloning: Makes a voice from about 3-30 seconds of audio, on both models

  • Professional voice cloning (beta): Higher-quality clones on TTS-2 only, capped per plan

  • Voice design (preview): Creates a new voice from a text description

  • Speech Reasoning (beta): Writes delivery directions for each line automatically

  • Languages: The marketing page claims 500+ with dialects, while the docs list 200+. Flash covers fewer.

  • Retired models: TTS-1 and TTS-1-Max were shut down on 2026-06-15, with requests rerouted to newer models automatically. TTS-1.5 Max and Mini are deprecated.

  • Speech-to-text and LLM router: Available on the same API, so one vendor covers listening, thinking and speaking

Pricing

  • How you pay: Pay-per-character API, with optional monthly plans that pre-buy credit at a discount

  • Free: No free plan. On-Demand has no monthly fee and bills only per character.

  • Creator: $25/mo

  • Builder: $100/mo

  • Developer: $300/mo, with 10,000 custom voices

  • Growth: $1,500/mo

  • Enterprise: Custom

  • TTS-2 Flash: $7-15 per 1M characters depending on plan

  • TTS-2: $12.50-25 per 1M characters, vs ElevenLabs' $40-80

  • Rollover: Subscription credits roll over for 3 months

  • HIPAA: A Growth-plan add-on

  • Caveat: The lowest rates, as low as $5 per 1M, need an Enterprise sales deal

Integrations

  • Platforms: Web Playground, a cloud REST and streaming API. No on-device or open-weight model is offered.

  • OpenAI-compatible endpoint: api.inworld.ai/v1 works with the OpenAI SDK, so existing OpenAI code can switch over by changing the address

  • Voice agent frameworks: LiveKit Agents plugin for TTS and STT, and Pipecat listed as a partner, let you use Inworld in real-time agents

  • Developer tools: Command-line tool, MCP server and a coding-agent skill

  • ElevenLabs migration tool: Open-source tool on GitHub that runs locally to help move from ElevenLabs

Platforms

  • Web Playground
  • REST API
  • Streaming API
❤️

What users love about Inworld TTS

  • ElevenLabs-level voices for a small fraction of the cost: Quality is on par with ElevenLabs for developers shipping voice at scale, which is why high-volume call builders get pointed to it

  • Natural fillers and emotion: Filler sounds and emotional delivery come out naturally, so back-and-forth conversation in consumer and companion apps sounds less scripted

  • Non-English voices sound native: Other languages sound authentic, not like an English voice reading a foreign script

  • One API for the whole voice stack: Speech-to-text, an LLM router and TTS come from one vendor instead of three separate services

😕

What users complain about Inworld TTS

  • Real prices need a sales call: List prices aren't competitive, and the real volume rate needs a sales call, which is hard to justify before testing with actual users

  • Forced model migrations every few months: TTS-1 gave way to 1.5 and then TTS-2 within about a year, and TTS-1 was switched off in June 2026, so early adopters had to re-test and migrate

  • No studio for non-coders: With no studio or no-code editor, creators looking to replace ElevenLabs Studio can't use it without writing code

  • Hard-to-forecast bills: Per-character billing makes monthly costs hard to predict for high-traffic consumer apps