Inworld Realtime STT

Muse Voice Transcribe is Meta’s first real-time audio perception model, delivering streaming automatic speech recognition (ASR), diarization, and endpointing in real time. An autoregressive multimodal model from the Muse Spark family, it processes audio in 80 ms chunks and decides dynamically whether to continue listening or emit text. Its adaptive delay changes the amount of audio context used for each word based on difficulty, balancing transcription accuracy with latency. The model is trained on more than 70 languages, with 25 extensively verified at launch, and natively supports arbitrary code-switching both within and between sentences. Language, keyword, and context biasing can further improve recognition accuracy for specific names, places, contacts, or terminology. Streaming diarization identifies speaker changes and distinguishes more than 20 speakers, while endpointing detects when speech begins and when a user finishes speaking.

Inworld TTS is a state-of-the-art text-to-speech platform designed to deliver ultra-realistic, context-aware speech synthesis and precise voice-cloning capabilities at a radically accessible price. The flagship model, TTS-1, is optimized for real-time applications and supports low-latency streaming (first audio chunk in ≈200 ms) as well as multiple languages (including English, Spanish, French, Korean, Chinese, and more). Developers can use instant zero-shot voice cloning (5-15 seconds of audio) or professional fine-tuned cloning, add voice-tags for emotion, style, and non-verbal sounds, and switch languages while preserving voice identity. The larger TTS-1-Max model (in preview) offers even more expressive speech and multilingual strength. The platform supports both API and portal access, streaming or batch mode, and is designed for everything from interactive voice agents and gaming characters to branded audio experiences.