narrate 0.1.1

Local text-to-speech with Kokoro and Chatterbox engines

narrate

Local text-to-speech with multiple engine support.

Install

pip install narrate[kokoro]       # Kokoro 82M — fast, runs on CPU
pip install narrate[chatterbox]   # Chatterbox 500M — high quality, emotion control
pip install narrate[all]          # Both engines + audio playback

Usage

from narrate import narrate

# Uses the best available engine and default voice
narrate("Hello world")

# Choose voice (second positional argument)
narrate("Hello world", "am_adam")        # male voice
narrate("Hello world", "bf_emma")        # British female
narrate("Hello world", "af_sarah")       # soft female

# Keyword style with speed control
narrate("Hello world", voice="af_heart", speed=1.2)

# Chatterbox with emotion control (0.0 = neutral, 1.0 = expressive)
narrate("Hello world", engine="chatterbox", emotion=0.8)

# Save to file without playing
narrate("Hello world", output="hello.wav", play=False)

Available Voices (Kokoro)

Voice ID	Name	Description
af_heart	Heart	Female, warm (default)
af_bella	Bella	Female, clear
af_nicole	Nicole	Female, professional
af_sarah	Sarah	Female, soft
af_sky	Sky	Female, bright
am_adam	Adam	Male, deep
am_michael	Michael	Male, natural
bf_emma	Emma	British female
bm_george	George	British male

# List all available voices programmatically
from narrate import list_voices
for v in list_voices():
    print(f"{v['id']:15} {v['name']:10} {v['description']}")

Engines

Engine	Params	Speed	Quality	Features
Kokoro	82M	Fast (CPU)	Good	9 voices, speed control
Chatterbox	500M	Moderate	Excellent	Emotion control, voice cloning

License

MIT