Local-first · runs on your Mac

A voice agent that runs entirely on your Mac.

Nia is a cascaded, on-device voice stack — Whisper ears, a Gemma brain, a Kokoro voice — wired together so every part is a swappable box. No cloud, no per-minute meter, no data leaving the machine.

16 GB Apple Silicon·No cloud·Open pipeline
nia-voice-01Cascaded speech · on-device
WhisperGemmaKokoro
Silero VAD + Smart Turn·Ollama brain·MLX-native

One stack, many studios

Every stage of the pipeline is exposed as a tool. Talk, interpret, dub, synthesize, clone and transcribe — all from the same on-device engine.

How it works

A cascaded pipeline: audio in, audio out, every box swappable behind a stable interface. Change the brain or the voice without rewiring.

1Mic
2VAD
3STT
4LLM
5TTS
6Speaker
Voices Studio

Fan one line across every voice.

Type once, add voices and languages, and generate them all in a batch. Preview each clip inline, then download WAV or MP3.

Open Voices Studio
Text
Welcome to Nia — your voice, on your machine.
af_heartEnglish
hf_alphaHindi
Generate
Dub & Interpreter

Cross the language barrier, live.

Interpret a conversation turn by turn, or redub a whole clip into a new language while preserving the original speaker's voice and timing.

Try the studios
ENWhere is the nearest station?
ES¿Dónde está la estación más cercana?
ENThank you very much.
Developers

Bring your own key.

A simple, OpenAI-shaped API for speech, voices and chat. Mint a key, call an endpoint, and metering shows up in your dashboard.

POST /v1/speech
curl https://localhost/v1/speech \
  -H "Authorization: Bearer $NIA_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "voice": "af_heart",
    "language": "en",
    "input": "Hello from Nia."
  }' --output reply.wav

Talk to Nia now.

No sign-up, no cloud round-trip. Grant mic access and start the conversation.

Open the Playground