voicebox-tts 0.0.2

Python text-to-speech library with built-in voice effects and support for multiple TTS engines.

voicebox

Python text-to-speech library with built-in voice effects and support for multiple TTS engines.

Listen to audio samples here: Audio Samples

# Example: Use gTTS with a vocoder effect to speak in a robotic voice

from voicebox import Voicebox
from voicebox.tts import gTTS
from voicebox.effects import Vocoder, Normalize

voicebox = Voicebox(
    tts=gTTS(),
    effects=[Vocoder.build(), Normalize()],
)

voicebox.say('Hello, world! How are you today?')

Setup

1. pip install voicebox-tts
2. Install the PortAudio library for audio playback.
   • On Debian/Ubuntu: sudo apt install libportaudio2
3. Install dependencies for whichever TTS engine(s) you want to use (see section below).

Supported Text-to-Speech Engines

Classes for supported TTS engines are located in the voicebox.tts.* modules.

Amazon Polly 🌐

Online TTS engine from AWS.

• Class: voicebox.tts.AmazonPolly
• Setup: pip install voicebox-tts[amazon-polly]

ElevenLabs 🌐

Online TTS engine with very realistic voices and support for voice cloning.

• Class: voicebox.tts.ElevenLabs
• Setup:
  1. pip install voicebox-tts[elevenlabs]
  2. Install ffmpeg or libav for pydub (docs)
  3. Get an API key and do one of the following:
     • Set environment variable ELEVEN_API_KEY=<api-key>; or
     • Set with import elevenlabs; elevenlabs.set_api_key('<api_key>'); or
     • Pass as parameter to class: voicebox.tts.ElevenLabs(api_key='<api_key>')

eSpeak NG 🌐

Offline TTS engine with a good number of options.

• Class: voicebox.tts.ESpeakNG
• Setup:
  • On Debian/Ubuntu: sudo apt install espeak-ng

Google Cloud Text-to-Speech 🌐

Powerful online TTS engine offered by Google Cloud.

• Class: voicebox.tts.GoogleCloudTTS
• Setup: pip install voicebox-tts[google-cloud-tts]

gTTS 🌐

Online TTS engine used by Google Translate.

• Class: voicebox.tts.gTTS
• Setup:
  1. pip install voicebox-tts[gtts]
  2. Install ffmpeg or libav for pydub (docs)

Pico TTS

Very basic offline TTS engine.

• Class: voicebox.tts.PicoTTS
• Setup:
  • On Debian/Ubuntu: sudo apt install libttspico-utils

Effects

Built-in effect classes are located in the voicebox.effects module, and can be imported like:

from voicebox.effects import CoolEffect

Here is a non-exhaustive list of fun effects:

• Bitcrusher
• Delay
• Flanger
• Glitch
• RingMod
• Vocoder

There is also support for all the awesome audio plugins in Spotify's pedalboard library using the special PedalboardEffect wrapper, e.g.:

from voicebox import Voicebox
from voicebox.effects import PedalboardEffect
import pedalboard

voicebox = Voicebox(
    effects=[
        PedalboardEffect(pedalboard.Reverb()),
        ...,
    ]
)

Examples

Minimal

# PicoTTS is used to say "Hello, world!"
from voicebox import Voicebox
voicebox = Voicebox()
voicebox.say('Hello, world!')

Pre-built

Some pre-built voiceboxes are available in the voicebox.examples package. They can be imported into your own code, and you can run them to demo:

# Voice of GLaDOS from the Portal video game series
python -m voicebox.examples.glados "optional message"

# Voice of the OOM-9 command battle droid from Star Wars: Episode I
python -m voicebox.examples.battle_droid "optional message"

Advanced

# Use eSpeak NG at 120 WPM and en-us voice as the TTS engine
from voicebox.tts import ESpeakConfig, ESpeakNG

tts = ESpeakNG(ESpeakConfig(speed=120, voice='en-us'))

# Add some voice effects
from voicebox.effects import Vocoder, Glitch, Normalize

effects = [
    Vocoder.build(),  # Makes a very robotic, monotone voice
    Glitch(),  # Randomly repeats small sections of audio
    Normalize(),  # Remove DC and make volume consistent
]

# Send audio to playback device, and save to speech.wav file
from voicebox.sinks import Distributor, SoundDevice, WaveFile

sink = Distributor([
    SoundDevice(),
    WaveFile('speech.wav'),
])

# Build the voicebox
from voicebox import Voicebox

voicebox = Voicebox(tts, effects, sink)

# eSpeak NG is used to say "Hello, world!" with a glitchy robot voice
voicebox.say('Hello, world!')

Command Line Demo

python -m voicebox -h               # Print command help
python -m voicebox "Hello, world!"  # Basic usage