Realtime speech-to-speech models
Realtime speech-to-speech models covers native audio-in/audio-out models and streaming APIs that converse in one real-time session (barge-in, low latency), replacing an STT-LLM-TTS cascade.
In brief
Realtime speech-to-speech models, in brief.
What it isRealtime speech-to-speech models covers native audio-in/audio-out models and streaming APIs that converse in one real-time session (barge-in, low latency), replacing an STT-LLM-TTS cascade.
Where it sitsOne of 24 categories in the Models layer. Models are the trained systems that do the work: language models, and models for speech, images, video, code, translation and forecasting. This layer covers both closed models reached through an API and open models you can download.
What we track18 products, including Azure OpenAI Realtime API, EVI (Empathic Voice Interface), Gemini Live API, GLM-4-Voice and Grok Voice Agent API.
The products
18 products in Realtime speech-to-speech models.
Each name opens a search for that product in our index.
ProductMakerIts own site
From our census of 2026-11-08. A product listed here is one that belongs in this category; the search answer says whether we have checked it.
Questions
Realtime speech-to-speech models, answered.
What is Realtime speech-to-speech models in AI infrastructure?Realtime speech-to-speech models covers native audio-in/audio-out models and streaming APIs that converse in one real-time session (barge-in, low latency), replacing an STT-LLM-TTS cascade.
Which layer of AI infrastructure is Realtime speech-to-speech models in?Realtime speech-to-speech models is in the Models layer. Models are the trained systems that do the work: language models, and models for speech, images, video, code, translation and forecasting. This layer covers both closed models reached through an API and open models you can download.
Which products are in Realtime speech-to-speech models?We track 18 products in Realtime speech-to-speech models, including Azure OpenAI Realtime API, EVI (Empathic Voice Interface), Gemini Live API, GLM-4-Voice, Grok Voice Agent API, Kimi-Audio, LLaMA-Omni and Mini-Omni. The full list is on this page.
Models
The other categories in Models.
3D generation & motionAvatar / digital humansBackground removal & mattingBenchmarks & leaderboardsCode modelsEmbedding modelsFrontier model APIsImage generation & editingImage upscaling & restorationLip-sync & dubbingMachine translation APIsModel hubs / registriesMultilingual / regional-language modelsMultimodal / vision-language modelsMusic & audio generationOpen-weight model familiesReasoning modelsRerankersSmall / on-device LLMsSpeech (STT/TTS)Time-series foundation modelsVideo generationWorld models