
by Inworld AI
Inworld TTS is a realtime text-to-speech API with voice cloning and voice design, aimed at consumer apps such as companions, tutors and games. It returns first audio in under 100 ms.
APIUsage-based
Step 1: Create an Inworld account and open the Portal.
Step 2: Generate an API key under Manage, API Keys and copy the Base64 credential.
Step 3: Set the key as the INWORLD_API_KEY environment variable.
Step 4: Install the JavaScript or Python SDK.
Step 5: Send a streaming request with your text and a voice to get audio back.
Step 6: Try voices and clones in the TTS Playground before building.
Both models can render 50 non-verbal sounds such as [laugh] and [sigh]. Only Realtime TTS-2 follows written direction for delivery, while the Flash model ignores it.
Yes. You can clone a voice from as little as 3 seconds of audio, or design a new one from a written description.
Use an API key from the Inworld Portal with the JavaScript or Python SDK, or send direct HTTP requests with Basic authentication.
The site says both models return first audio in under 100 ms, and as low as 50 ms for the faster one.
Inworld AI EngineInworld AI provides realtime voice models and model inference through an API, aimed at consumer applications such as companions, tutors and games.
Inworld AIInworld AI uses AI for AI runtime and character technology for interactive NPCs, game dialogue, and realtime character behavior.
OpenAI Speech to TextOpenAI Speech to Text applies AI to AI speech-to-text API for transcribing and translating audio with OpenAI speech models.
OpenAI Realtime APIOpenAI's Realtime API lets developers build speech-to-speech voice agents that work directly with audio, keep conversation state and call tools. It is for developers building voice assistants and other low-latency conversational apps.