CODEWITHSUNDEEP
pythontext-to-speechspeech
Rao
Rao

Reputation: 2962

How to convert text to speech in python

I would like to now how to convert text to speech in python.

In .NET i used

Dim SAPI

Msg = 'Hi this is a test'

SAPI = CreateObject("sapi.spvoice")
SAPI.Speak(Msg)

Upvotes: 4

Views: 11856

Answers (8)

Kayemba Luwaga
Kayemba Luwaga

Reputation: 47

If you have a good processor/GPU, you can use this HuuggingFace transformer code for the best free results! Perhaps the quality is better than gtts!

# Get dependencies
# pip install soundfile transformers datasets sentencepiece

from transformers import SpeechT5Processor, SpeechT5ForTextToSpeech, SpeechT5HifiGan
from datasets import load_dataset
import torch
import random
import string
import soundfile as sf

device = "cuda" if torch.cuda.is_available() else "cpu"

# load the processor
processor = SpeechT5Processor.from_pretrained("microsoft/speecht5_tts")
# load the model
model = SpeechT5ForTextToSpeech.from_pretrained("microsoft/speecht5_tts").to(device)
# load the vocoder, that is the voice encoder
vocoder = SpeechT5HifiGan.from_pretrained("microsoft/speecht5_hifigan").to(device)
# we load this dataset to get the speaker embeddings
embeddings_dataset = load_dataset("Matthijs/cmu-arctic-xvectors", split="validation")

# speaker ids from the embeddings dataset
speakers = {
    'clb': 2271,  # US female
    'slt': 6799   # US female
}

def save_text_to_speech(text, speaker=None):
    # preprocess text
    inputs = processor(text=text, return_tensors="pt").to(device)
    if speaker is not None:
        # load xvector containing speaker's voice characteristics from a dataset
        speaker_embeddings = torch.tensor(embeddings_dataset[speaker]["xvector"]).unsqueeze(0).to(device)
    else:
        # random vector, meaning a random voice
        speaker_embeddings = torch.randn((1, 512)).to(device)
    # generate speech with the models
    speech = model.generate_speech(inputs["input_ids"], speaker_embeddings, vocoder=vocoder)
    if speaker is not None:
        # if we have a speaker, we use the speaker's ID in the filename
        output_filename = f"{speaker}-{'-'.join(text.split()[:6])}.mp3"
    else:
        # if we don't have a speaker, we use a random string in the filename
        random_str = ''.join(random.sample(string.ascii_letters+string.digits, k=5))
        output_filename = f"{random_str}-{'-'.join(text.split()[:6])}.mp3"
    # save the generated speech to a file with 16KHz sampling rate
    sf.write(output_filename, speech.cpu().numpy(), samplerate=16000)
    # return the filename for reference
    return output_filename

# generate speech with a US female voice
save_text_to_speech("Python is my favorite programming language", speaker=speakers["slt"])

# a challenging text with all speakers
text = """In his miracle year, he published four groundbreaking papers.
These outlined the theory of the photoelectric effect, explained Brownian     motion,
introduced special relativity, and demonstrated mass-energy     equivalence."""

for speaker_name, speaker in speakers.items():
    output_filename = save_text_to_speech(text, speaker)
    print(f"Saved {output_filename}")
# random speaker
output_filename = save_text_to_speech(text)
print(f"Saved {output_filename}")

Upvotes: 0

Peadar Coyle
Peadar Coyle

Reputation: 2243

If you want access to a ton of voices. We have over 500.

Here's a snippet

python
import apiaudio 
import os


apiaudio.api_key = os.environ['APIKEY']
first_track = apiaudio.Orchestrator.create_audio(scriptText="Hello World my first audio track", 
                                                 voice="Ryan",
                                                 soundTemplate="jakarta")
print(first_track)

You just need a FREE api key. Have a look at http://www.api.audio

Upvotes: -1

Nyi Naung Naung
Nyi Naung Naung

Reputation: 21

Here is Male's and Female's voices function created by myself.
Just define a file name and save it.
Now you can import it into another file and reuse it again and again.

pip install pyttsx3

import pyttsx3
def femaleVoice(text):
    print("Program : "+text)
    engine = pyttsx3.init()
    voices = engine.getProperty('voices')
    engine.setProperty('voice', voices[-1].id)
    engine.say(text)
    engine.runAndWait()

def maleVoice(text):
    print("Program : "+text)
    pyttsx3.speak(text)

femaleVoice("There we go.")#Text
maleVoice("There we go.")

Upvotes: 1

Nyi Naung Naung
Nyi Naung Naung

Reputation: 21

# pip install pywin32
# pip install pyttsx3
 
import pyttsx3

pyttsx3.speak('Hello Woeld')

Upvotes: 1

Ashish Shukla
Ashish Shukla

Reputation: 11

import pyttsx3
speaker=pyttsx3.init()
speaker.say("Your message")
speaker.runAndWait()

Upvotes: 1

Aakash Gupta
Aakash Gupta

Reputation: 13

You can do it by using the gTTS module. It converts the text to speech. The second module you have to use is playsound to play the converted text.

    from gtts import gTTS #pip install gtts
    import playsound #pip install playsound
    import os

    my_aud = gTTS("hello how are you") #converts the text into speech
    my_aud.save('demo.mp3') #save the file with .mp3 extension
    playsound('demo.mp3') #to play it
    os.remove('demo.mp3')

Upvotes: 0

Anil_M
Anil_M

Reputation: 11443

I know its real late to answer here, But I thought I would post here since I have solution based on TTS conversion using SAPI in python, which was OP's original question.

This may be useful for anyone else looking for solution using SAPI in python. 

from win32com.client import constants, Dispatch

Msg = "Hi this is a test"

speaker = Dispatch("SAPI.SpVoice")  #Create SAPI SpVoice Object
speaker.Speak(Msg)                  #Process TTS
del speaker                         #Delete speaker object and free up memory

Upvotes: 2

Sudeepth Patinjarayil
Sudeepth Patinjarayil

Reputation: 356

You can achieve it by pyttsx module. it uses default MS speech recognition system.

import pyttsx

engine = pyttsx.init()
engine.say("Your Message")
engine.runAndWait()

Upvotes: 3

Related Questions