paratran 0.2.1

REST API for audio transcription using parakeet-mlx

Paratran

REST API for audio transcription on Apple Silicon, powered by parakeet-mlx.

Parakeet is #1 on the Open ASR Leaderboard and runs ~30x faster than Whisper on Apple Silicon via MLX.

Requirements

• macOS with Apple Silicon (M1/M2/M3/M4)
• Python 3.11+
• ~2 GB memory for the default model

Quick Start

Run without installing:

uvx paratran

Install

uv (recommended)

uv tool install paratran
paratran

pip

pip install paratran
paratran

From source

git clone https://github.com/briansunter/paratran.git
cd paratran
uv sync
uv run paratran

Usage

# Default settings
paratran

# Custom model cache location
paratran --model-dir /Volumes/Storage/models

# Custom host and port
paratran --host 127.0.0.1 --port 9000

# Different model
paratran --model mlx-community/parakeet-tdt-1.1b-v2

All options can also be set via environment variables:

CLI Flag	Env Var	Default
--model	PARATRAN_MODEL	mlx-community/parakeet-tdt-0.6b-v3
--model-dir	PARATRAN_MODEL_DIR	HuggingFace default (~/.cache/huggingface)
--host		0.0.0.0
--port		8000

API

GET /health

curl http://localhost:8000/health

{
  "status": "ok",
  "model": "mlx-community/parakeet-tdt-0.6b-v3",
  "model_dir": "/Volumes/Storage/models"
}

POST /transcribe

Upload an audio file (wav, mp3, flac, m4a, ogg, webm):

curl -X POST http://localhost:8000/transcribe -F "file=@recording.m4a"

{
  "text": "Hello world, this is a test.",
  "duration": 3.52,
  "processing_time": 0.176,
  "sentences": [
    {
      "text": "Hello world, this is a test.",
      "start": 0.0,
      "end": 3.52,
      "tokens": [
        { "text": "Hello", "start": 0.0, "end": 0.48 },
        { "text": " world", "start": 0.48, "end": 0.8 }
      ]
    }
  ]
}

Interactive API docs are available at http://localhost:8000/docs.

License

MIT