Search the full model catalog.

Google Gemini 3.8 Live is a low-latency audio model for voice agents. It streams natural 24 kHz speech, supports tool calling, and optional Search grounding.

GPT‑Live‑1 is OpenAI’s full‑duplex voice model for real-time conversation. It streams speech and transcripts and can delegate reasoning and tools to a backend model.

Stream live speech and get translated speech plus live captions with low delay. Made by OpenAI for calls, meetings, broadcasts, and video chat translation.

Build low-latency voice agents with OpenAI’s GPT‑Realtime 2.1 Mini. It takes live audio or text and replies with spoken audio plus a transcript. ([developers.openai.com](https://developers.openai.com/api/docs/models/gpt-realtime-2.1-mini))

OpenAI's GPT Realtime 2.1 runs speech-to-speech conversations with configurable reasoning and tool calls. It’s built for voice agents that handle noise and interruptions.

Multilingual text-to-speech from OpenBMB: 2B parameters, 30 languages, 48 kHz output. Clone a voice from a short clip or describe a new one in words, with audio streamed back as it is generated.

Mistral AI's 4B streaming speech-to-text model. It writes out microphone audio in 13 languages while the speaker is still talking, with a transcription delay you set.

Streaming text-to-speech from OpenMOSS that sends audio in chunks while the rest of the text is still being synthesized. Clones a voice from one reference clip and speaks 20 languages.

A real-time voice conversation tool using ElevenLabs' AI voice agents. Customize voices, behaviors, and languages for interactive AI experiences.

GPT Mini Realtime enables low-latency, bidirectional streaming for voice and text. Build interactive, responsive AI experiences that feel natural and immediate.

GPT Realtime enables low-latency, bidirectional streaming for voice and text. Build interactive, responsive AI experiences that feel natural and immediate.

PersonaPlex is NVIDIA's full-duplex speech-to-speech model for live voice conversations. A text prompt sets the agent's role and the facts it uses, and one of 18 preset voices sets how it sounds.