Skip to content
English

Switch theme

Discover▾

Not sure where to start? This week’s hottest software, models and stacks in three minutes.

AI Apps▾

AI software people use: from assistants like ChatGPT to tools for coding, video and workflows, picked by purpose.

For Agents▾

Software for AI: tools that let your agent (Claude Code, Codex, Cursor…) browse, read docs, run code and remember.

Models▾

Choose models, estimate cost, self-host: prices, rankings, benchmarks, free tiers and compute.

Solutions▾

A goal or an error message? Ready-made stacks, steps and fixes by scenario.

Learn▾

A systematic course from zero to the frontier, with an algorithm library, must-read papers and tutorials.

Frontier▾

Daily AI news, weekly highlights, the latest papers and how AI is changing every discipline.

// Software stack

Local voice assistant

Speech recognition, a local LLM and speech synthesis all running on your machine, without cloud APIs.

4 pieces4 setup stepsscenario: Run models on your own machine

What goes in it

  1. 1

    faster-whisper Speech recognition & synthesis Open source

    Speech to text

    Faster Whisper transcription with CTranslate2

    ★ 26k
  2. 2

    Ollama Local inference & serving Open source

    Local LLM

    Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.

    ★ 184k
  3. 3

    CosyVoice Speech recognition & synthesis Open source

    Text to speech, strong in Chinese

    Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.

    ★ 24k
  4. 4

    Kokoro-FastAPI optional Speech recognition & synthesis Open source

    Lightweight TTS server

    Dockerized OpenAI-compatible wrapper for Kokoro-82M text-to-speech w/multiplatform CPU, AMD, NVIDIA GPU PyTorch; multi-speaker, clone-tuning, caption timestamps, SSML, optional readalong web UI

    ★ 5.6k

How to set it up

  1. 01Speech-to-text with faster-whisper (officially up to 4× faster than openai/whisper at the same accuracy)
  2. 02Run a local model with Ollama in the middle
  3. 03Use CosyVoice for Chinese speech and Kokoro for lightweight English speech
  4. 04Measure end-to-end latency before choosing model sizes

✓ Good fit

  • Offline use, no voice uploads

✗ Look elsewhere if

  • Lowest latency and most natural voice: cloud voice services are more mature

Data updated: AI software & hot ranks · Solutions & stack guides(UTC+8)