All models
Yenisei
Yenisei Voice
Speech recognition: voice input in the chat and the app
Text
Audio
Tools
- Type
- Chat
- Context
- 32K tokens
- Russian
- high
- Input price
- 4 ₽ / 1M tokens
- Output price
- 12 ₽ / 1M tokens
- Release date
- August 2026
chat/completions
import OpenAI from "openai"const client = new OpenAI({ baseURL: "https://api.yenisei.ru/v1", apiKey: process.env.YENISEI_API_KEY,})const stream = await client.chat.completions.create({ model: "yenisei-voice", messages: [{ role: "user", content: "Hi!" }], stream: true,})for await (const chunk of stream) { process.stdout.write(chunk.choices[0]?.delta?.content ?? "")}About the model
Yenisei Voice turns speech into text: send an audio recording and get a transcript. It recognizes Russian speech reliably, preserving numbers, dates and terminology. You can call it through the API from your own product for dictation, call transcription and voice input; in the chat and the app, it is the same model behind the microphone button.
Strengths
- Speech to text for voice input
- Works in the web chat and the desktop app
- The transcript can be edited before sending
Where to use it
- Dictating a question instead of typing
- Giving an agent a long assignment by voice
- Input from a phone, where typing is awkward