These models hold a spoken conversation: they listen and reply with speech without a separate recognition, text and synthesis pipeline. They power phone voice bots and in-app assistants. Check response latency, support for your languages, the license and GPU requirements.
Xiaomi models for reasoning and agents: from the compact MiMo-7B to MiMo-V2.6-Pro with 1.02 trillion parameters. The larger versions understand text, images, video and audio, with a 1M token context. Languages: English and Chinese.
Sber open models with strong Russian language support and local context, from 10B-A1.8B to 702B, all MIT. GigaChat3.1-Audio handles recordings up to two hours; GFusion is a fast diffusion text version.
Tiny audio-understanding models for smartphones: they listen to speech, music and ambient sounds and answer in text - describing a recording and answering questions about it. They run on the device itself; prompts and answers are in English - no other languages are present in the training data.
NVIDIA models for agents and reasoning, optimized to run fast on its GPUs. Nemotron 3 is a Mamba and MoE hybrid from 4B to 550B; Nano Omni handles video, audio and images (English only).
Models with a new architecture for on-device use: fast on a regular CPU and on phones. Versions for data extraction, RAG and tools, plus LFM2.5-VL for images and voice LFM2.5-Audio.
Models from Meituan, China's largest delivery service. LongCat-Flash adjusts compute to query complexity; LongCat-2.0 has 1.6 trillion parameters under MIT. Omni models (Flash-Omni, Next) and AudioDiT speech synthesis too.
StepFun MoE models built for fast, low-cost work: with 196 billion parameters, Step-3.5/3.7-Flash use about 11 billion per token. Compact Step3-VL-10B for images and voice Step-Audio 2 mini are available.
Models that listen to speech, sounds and music and answer questions about them. Audio Flamingo Next handles recordings up to 30 minutes. Research use only.
A voice assistant that listens and speaks at the same time, with no delay for recognition and synthesis. Hibiki does simultaneous speech-to-speech translation between several European languages.
A small model that sees, hears and replies by voice in real time, and can clone a voice. Voice dialogue in English and Chinese, text in 30+ languages.
A voice conversation partner based on Moshi that listens and speaks at the same time and can be interrupted. The role is set by text, the voice by a sample recording. English only.
Russian-language fine-tunes of open models (Mistral, Qwen, Llama) by the independent Vikhr team, with compact versions for a regular PC. Borealis is an audio model for recognizing and understanding Russian speech.
Models that understand text, images, audio and video and reply by voice in real time. Qwen3-Omni speaks 10 languages, including Russian.
A general-purpose audio model: speech recognition, answering questions about sounds, detecting emotions and voice dialogue. Trained on 13 million hours of audio; languages are English and Chinese.
Speech and text translation across roughly a hundred languages, including Russian: speech to text, speech to speech, and streaming translation that keeps intonation.
An open model can run on your own server: data stays in-house, there is no per-request fee, and the model can be fine-tuned on your documents.
