Realtime TTS
Text-to-speech API (Realtime TTS-2 and TTS-2 Flash) with voice cloning and voice design, billed per million characters.
Find alternatives to Realtime TTS
What it does
- Text to speech
Features 8
- Voice directionDescribe the delivery in plain words and the model performs it, inline or for the whole request.
- Voice cloning and designClones a voice from 3 seconds of audio or designs one from a written description.
- Timestamps and lip-syncReturns word and character timings for captions and visemes for lip-sync.
- Custom pronunciationWords can be written in IPA inline so names and brands sound right.
- OpenAI-compatible endpointPoint the OpenAI SDK at api.inworld.ai/v1 and pick an Inworld voice.
- Long-form and batchSends up to 100,000 characters as one async job; batch jobs bill 20% less per character.
- CLI and MCP serverRuns inworld tts synthesize from the shell, or lets a coding agent call TTS through the MCP server.
- Speech ReasoningReads the conversation and directs the delivery of each line without tags; in beta.
How it compares
-
Sonic / Ink
Sonic 3.6 rates above both Inworld models, Realtime TTS-2 and Realtime TTS-2 Flash.
Official documentation · 13 Oct 2026
Sources
- Pricing
-
Pricing page: On-Demand pay as you go ($25 per 1M characters TTS-2), Creator $25/mo through Growth $1,500/mo, Enterprise custom; up to 70 minutes free.
- Description
-
Company disclosure · 10 Oct 2026
TTS page: Realtime TTS-2 and TTS-2 Flash; voice cloning, voice design; 200+ languages.
- What it does
-
Company disclosure · 10 Oct 2026
TTS page: Realtime TTS-2 and TTS-2 Flash; voice cloning, voice design; 200+ languages.
- Sold within
-
Sold on its own; no parent offering.
- Name
-
Company disclosure · 10 Oct 2026
Name as published.
- URL
-
Company disclosure · 10 Oct 2026
Product page.
- Deployment
-
Company disclosure · 10 Oct 2026
TTS page: REST API and WebSocket endpoints, API-key authentication, TTS Playground.
- Interfaces
-
Official documentation · 11 Oct 2026
REST, streaming and WebSocket synthesis endpoints; "Python SDK: Use the inworld-tts package"; "Node.js SDK: Use the @inworld/tts package"; "Inworld CLI ... inworld tts synthesize|clone|design"; "Inworld MCP server ... Exposes operations as tools — TTS synthesis and previews, voice design".
- Modalities
-
Official documentation · 12 Oct 2026
Page: 'Text-to-speech price vs the market'.
Also from Inworld AI
-
Realtime STT API service
Speech-to-text API (Inworld STT-1) that transcribes streaming or complete audio in 30+ languages with turn detection, returning voice-profile signals for emotion, vocal style, accent, age and pitch alongside the transcript.
-
Realtime API API service
Speech-to-speech voice-agent API in which one WebSocket session runs Inworld speech recognition with voice profiling, a chosen LLM from 100+ with tool calling and turn detection, and Realtime TTS-2 voice output.
-
Realtime Router Platform
OpenAI-compatible LLM gateway that sends each request to one of 100+ models from OpenAI, Anthropic, Google and others by rules on user attributes, context, A/B splits or cost, with failover and provider rates passed through at zero markup.
-
Inworld Compute Infrastructure service
Dedicated NVIDIA B200 GPUs for high-volume realtime workloads such as LLM inference, dedicated TTS serving and custom model hosting, with Kubernetes access or Inworld-managed deployment, and deployed models routable through Inworld Router.
-
Inworld Inference Model API
Inworld Inference provides API access to text, image, video and decision models.
Open Inworld AI in the directory
Something wrong here? Send a correction — quote this product id: inworld-realtime-tts.