Questions tagged [text-to-speech]
Text-to-speech or speech synthesis is the artificial production of human speech.
text-to-speech
3,771
questions
0
votes
0
answers
10
views
Avatar failed to start. Error: InvalidCharacterError: Failed to execute 'atob' on 'Window': The string to be decoded is not correctly encoded
// utilty.js
export const fetchIceCredentials = async () => {
try {
const response = await axios.get('https://westus2.tts.speech.microsoft.com/cognitiveservices/avatar/relay/token/v1', {...
-2
votes
0
answers
62
views
Confused about text to speech generation using C# on Windows - System.Speech vs. Microsoft Speech Platform [closed]
I would like to do text to speech generation on Windows using C#. I am developing an application which will be deployed on the backend. Thus I am not developing a desktop application. I don't want to ...
0
votes
0
answers
14
views
Google TTS SSML isn't changing languages with <lang> tag
I'm trying to get the Google TTS API to pronounce foreign words properly, but can't figure it out. Aside from their demo of pronouncing "chat" in French, almost anything else I try is ...
0
votes
0
answers
21
views
Bark/Coqui voice cloning on CPU restarts computer
I am using CoquiTTS and Bark to create a text to speech like below. Each time I run this program on my CPU based machine, the CPU spikes to 100% a few times and eventually after a few minutes the ...
0
votes
1
answer
19
views
how to set persian language to flutter_tts package
I am going to change the text to voice in flutter and I'm installed flutterTts package so its just read English text and its unable to read Persian language.
I also set the language to
flutterTts....
0
votes
1
answer
36
views
Azure TTS, Python SDK Error 1007: Data at the root level is invalid
Getting this error code when passing xml to Azure, assuming the issue lies with how I've got the xml set up.
Here is my code building the xml:
from lxml.builder import ElementMaker
ns = {
...
0
votes
0
answers
27
views
Alternative solution to Google TTS API in creating TTS Windows app with Python
I am making a text to speech software on Windows OS using Python. I found the google text to speech api. It's pretty good, but I want it to use in offline with downloadable speech packs like Speech ...
0
votes
0
answers
38
views
How to register voice for TTS in windows 11?
I have some troubles to use 2 additional voices, in my case i try to use Pablo (Spanish - Spain) and George (English - GB). I develop a app in python/Django, from the front i sent a JSON with the ...
0
votes
0
answers
10
views
How to get access to `TextToSpeechService` instance on Android?
I need to generate spoken text as raw audio stream (e.g. an array of PCM floats). TextToSpeechService appears to have exactly the interface I need. How can I get it for the default system voice/engine?...
0
votes
0
answers
21
views
Knowing the format of dataset a pretrained model was trained on
i am working on a Multilingual TTS project , and developing a TTS for my regional language by using a pretrained model from Hugging Face hub , the model i am trying to fine tune is facebook-mms-tts ...
2
votes
1
answer
40
views
How to play generated audio from Edge TTS directly to speaker without saving it first?
This is the code for saving the audio from edge tts
import asyncio
import edge_tts
voices = [ 'en-US-GuyNeural']
text = "Hi this is the test"
voice = voices[0]
output_file = "...
0
votes
1
answer
45
views
Audio retrieval Using Azure TTS API in C#, missing audio for certain words
I am using my C# code with "https://eastus.tts.speech.microsoft.com/cognitiveservices/v1" to get audio for English words. It was working well until I suddenly noticed that for certain words, ...
0
votes
0
answers
37
views
PyTorch TTS producing Illegal CUDA memory access
I am trying to run couqi TTS but when I try to synthesize audio, Illegal cuda memory access appears.
RuntimeError: CUDA error: an illegal memory access was encountered
CUDA kernel errors might be ...
1
vote
1
answer
29
views
Inconsistent HTTP Visibility in Wireshark for Azure API Calls from C# vs. Python and CURL
I am using the Azure API to get audio for words. This is my code in C#, and it worked fine until I noticed that for some words it returns empty audio.
string subscriptionKey = Environment....
0
votes
0
answers
10
views
The WinError126 error keeps appearing in the pytorch part of TTS.api. Is there a way to fix it?
Code:
from TTS.api import TTS
tts = TTS("tts_models/multilingual/multi-dataset/xtts_v2", gpu=False)
tts.tts_to_file(text="It took me quite a long time to develop a voice, and now that ...