Skip to main content

ailia AI Voice

Project description

ailia AI Voice Python API

!! CAUTION !! “ailia” IS NOT OPEN SOURCE SOFTWARE (OSS). As long as user complies with the conditions stated in License Document, user may use the Software for free of charge, but the Software is basically paid software.

About ailia AI Voice

ailia AI Voice is a library for speech synthesis using AI. It provides APIs for C# for Unity and for C for native applications. By using ailia AI Voice, it is possible to easily implement AI-based speech synthesis in applications.

ailia AI Voice can perform speech synthesis offline, only on edge devices, without the need for cloud connectivity. It also supports the latest GPT-SoVITS, enabling speech synthesis in any voice timbre.

Install from pip

You can install the ailia AI Voice free evaluation package with the following command.

pip3 install ailia_voice

Install from package

You can install the ailia AI Voice from Package with the following command.

python3 bootstrap.py
pip3 install ./

Usage

import ailia_voice

import librosa
import time
import soundfile

import os
import urllib.request

# Load reference audio
ref_text = "水をマレーシアから買わなくてはならない。"
ref_file_path = "reference_audio_girl.wav"
if not os.path.exists(ref_file_path):
	urllib.request.urlretrieve(
		"https://github.com/axinc-ai/ailia-models/raw/refs/heads/master/audio_processing/gpt-sovits/reference_audio_captured_by_ax.wav",
		"reference_audio_girl.wav"
	)
audio_waveform, sampling_rate = librosa.load(ref_file_path, mono=True)

# Infer
voice = ailia_voice.GPTSoVITS()
voice.initialize_model(model_path = "./models/")
voice.set_reference_audio(ref_text, ailia_voice.AILIA_VOICE_G2P_TYPE_GPT_SOVITS_JA, audio_waveform, sampling_rate)
buf, sampling_rate = voice.synthesize_voice("こんにちは。今日はいい天気ですね。", ailia_voice.AILIA_VOICE_G2P_TYPE_GPT_SOVITS_JA)
#buf, sampling_rate = voice.synthesize_voice("Hello world.", ailia_voice.AILIA_VOICE_G2P_TYPE_GPT_SOVITS_EN)

# Save result
soundfile.write("output.wav", buf, sampling_rate)

API specification

https://github.com/axinc-ai/ailia-sdk

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

ailia_voice-1.2.0.0.tar.gz (2.0 MB view details)

Uploaded Source

Built Distribution

ailia_voice-1.2.0.0-py3-none-any.whl (2.0 MB view details)

Uploaded Python 3

File details

Details for the file ailia_voice-1.2.0.0.tar.gz.

File metadata

  • Download URL: ailia_voice-1.2.0.0.tar.gz
  • Upload date:
  • Size: 2.0 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.1.1 CPython/3.12.7

File hashes

Hashes for ailia_voice-1.2.0.0.tar.gz
Algorithm Hash digest
SHA256 f7012119e3e93c552fc1e8bb04cbd54859fa19956cd0610d3b0814f0a5f68caf
MD5 8cb8a5d99d3d0a2e74bd0e4a8ed67b7a
BLAKE2b-256 6184864a597e1e326297cfac15bb4bae1243db087caf6093e2cbe2251b3260ac

See more details on using hashes here.

File details

Details for the file ailia_voice-1.2.0.0-py3-none-any.whl.

File metadata

File hashes

Hashes for ailia_voice-1.2.0.0-py3-none-any.whl
Algorithm Hash digest
SHA256 9b7cc2ff52e89eb212e84edfb931e2d3c5071635437e1e653d9aa228b65edd01
MD5 13f26dfe040d2cba0f8587055ef69302
BLAKE2b-256 e43077a6335fc358d12ba622b6b915d4dc54f4a84f73e3c69559f2cb63d0f2dd

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page