Building a Local AI Voice Assistant with Whisper and Ollama

Building a Local AI Voice Assistant with Whisper and Ollama

A fully local voice assistant — where your speech never leaves your device — is achievable with three components: Whisper for speech-to-text, Ollama for language model inference, and a TTS engine for voice output. The result is a private, always-available assistant that works offline and costs nothing to run.

Hardware recommendation: The full stack (Whisper medium, Mistral 7B, Coqui TTS) runs well on a Mac Mini M4 or any PC with 8GB+ VRAM. For budget hardware that handles all three components, LLMHardware.io has a dedicated voice AI build guide.

Stack Components

Speech-to-text: faster-whisper (Python library) using Whisper medium.en for English, or Whisper large-v3 for multilingual. Text-to-speech: Coqui TTS (open-source, cloneable voices) or Piper TTS (faster, optimized for real-time). LLM: any Ollama model — Mistral 7B or Llama 3.1 8B work well for conversational tasks. Wake word: OpenWakeWord (free, CPU-based) for hands-free activation.

Latency Optimization

Total latency is the sum of STT + LLM + TTS processing times. For a natural-feeling assistant, target under 2 seconds total. Whisper medium processes speech in roughly 0.5-1x real-time. LLM time-to-first-token (TTFT) is typically 100-400ms for 7B models. TTS adds 200-500ms depending on output length. Key optimization: stream TTS output — start playing audio as soon as the first sentence is complete rather than waiting for the full response.

Home Automation Integration

Connect your local voice assistant to Home Assistant via the REST API. Add a function-calling setup where the LLM can invoke home automation commands ("turn on the kitchen lights") by generating structured JSON output. This creates a fully local smart home assistant that works without internet, never sends commands to Amazon or Google, and can be customized with complete control over what it does and doesn't do.

Comments

Post a Comment

Popular posts from this blog

AMD RX 9070 XT for Local LLMs: ROCm Performance Guide (2026)

The AMD RX 9070 XT launched in early 2026 at $599 with 16GB GDDR6 and 648 GB/s memory bandwidth. For local LLM users who want a mid-range GPU without NVIDIA prices, this changes the calculus significantly. Here is what it actually delivers. RX 9070 XT Specs vs Competition GPU VRAM Bandwidth Price LLM Score RX 9070 XT 16 GB 648 GB/s $599 ~60 tok/s RTX 4070 Ti Super 16 GB 672 GB/s $799 ~62 tok/s RTX 4080 Super 16 GB 736 GB/s $999 ~68 tok/s RTX 4090 24 GB 1,008 GB/s ~$1,100 ~90 tok/s At $599 with 16GB VRAM, the RX 9070 XT is the best value GPU for local LLMs in the mid-range tier in 2026. See the full comparison at LLMHardware.io's AMD GPU guide . ROCm Setup on Linux (2026) # Ubuntu 22.04/24.04 sudo apt install rocm-hip-libraries hip-base # or use the AMD installer: wget https://repo.radeon.com/amdgpu-install/6.3/ubuntu/jammy/amdgpu-install_6.3.60300-1_all.deb sudo dpkg -i amdgpu-install*.deb sudo amdgpu-install --usecase=rocm,lrt,openclsdk # Verify ROCm sees your GPU r...
Read more

llama.cpp flash attention: how to enable and benchmark

Image
Flash attention computes attention with far less memory traffic. The math is identical; the memory movement is not. In llama.cpp it matters most in two situations: long context windows and tight video memory (VRAM). With flash attention enabled, the key-value cache shrinks substantially. A 32k-token context window becomes realistic on a 16GB card, and the prompt-processing phase speeds up, so long documents get ingested faster. The catch is compatibility: not every model and quantization combination supports it, and on some setups the speedup is modest. If you run short chats on a strong GPU, you may barely notice. Where it shines is retrieval-augmented generation (RAG) and long-document work on mid-range cards. Enable it, compare your tokens per second, and keep it if your workload benefits. For the common case of pasting a long PDF and asking questions, it is close to free performance. See how context length changes VRAM needs .
Read more

SillyTavern with Local LLMs: Complete Setup for AI Companions

Image
SillyTavern is the most feature-rich frontend for character-based AI conversations. What began as an AI roleplay tool has evolved into a powerful platform with persona management, memory systems, extensive prompt engineering tools, and connections to every major local inference backend. Here's how to set it up with local models. Quick connect: SillyTavern connects to Ollama, KoboldCpp, llama.cpp server, and TabbyAPI (ExLlamaV2) out of the box. Any of the hardware setups at LLMHardware.io provides a solid backend for SillyTavern. Installation Install via git: git clone https://github.com/SillyTavern/SillyTavern && cd SillyTavern && npm install then node server.js . Access at localhost:8000. For persistent installation, use the included start.sh script. SillyTavern uses Node.js and runs on any platform. The companion app (STMP) enables mobile access to your SillyTavern instance via Tailscale or local network. Character Cards and the TavernAI Format Chara...
Read more