1,097 questions
1
vote
0
answers
75
views
How to implement non-blocking async checks between turns in Pipecat Flows (0.0.18)?
I’m working with the latest version of Pipecat and Pipecat Flows (0.0.18), and I’m trying to implement a pattern where the bot can continue interacting with the user while an async background task ...
- 11
0
votes
0
answers
41
views
Graph Hopper Version 9.0 Not Loading Profiles
I am using OsmDroid to build map offline and achieve turn by turn navigation along with voice over instruction which I believe could be achievable by GRAPHHOPPER library version 9.0.
So these are my ...
1
vote
0
answers
231
views
Google Text-to-Speech Missing other Voices and SSML Options
On the Google Text-to-Speech demo page, I used to be able to choose from multiple voices, test SSML on browser, and listen to the output directly in the browser. However, those options are now gone, ...
0
votes
1
answer
108
views
How to create Voice Input in my own app in Android Auto?
In this page, it states that you can use Voice Input "to support building features such as an in-app digital assistant."
I've been searching, but I can't find anything related to this voice ...
1
vote
0
answers
78
views
Flutter can't play audio with recording
I am making a hearing aid application in flutter for those who can't hear properly, idea is sound that microphone get user can change its frequency, pitch other settings using slider or something else,...
- 21
0
votes
1
answer
28
views
Play a menu to a participant in a conference
I have built an integration with Twilio Voice. My software has a built in queue mechanism, so we dont want to hand off the management of the Queue to Twilio.
We use conferences to place callers into a ...
- 5,719
3
votes
1
answer
359
views
Twilio Stream with Ambience Sound in Node.js
I am using https://github.com/twilio-labs/call-gpt this code for one of my project.
Everything works well but I am not able to add ambiance sound like office sound that user can hear so AI can process ...
- 91
0
votes
1
answer
398
views
discord.py - Voice Client not playing source
I was recently creating a Discord Bot and wanted to create a /effect boom command. After running the command, the client joins the channel and should play the specified source in the code.
I don't ...
- 1
0
votes
1
answer
161
views
Customize the prompt message to notify customers about their upcoming appointments in Amazon connect contact FLows in Salesforce voice
I have an use case to make automated outbound calls to customers notifying them of their upcoming appointments in the next 5 days in Salesforce omnichannel voice. I want to customize the prompt ...
0
votes
0
answers
454
views
How to solve AttributeError: 'Audio' object has no attribute 'transcribe'?
I am trying to do a voice recognition bot.
I wrote following code:
app.py
from dotenv import load_dotenv
import os
load_dotenv()
from interface import AudioInterface
interface=AudioInterface()
text=...
- 1,311
0
votes
1
answer
108
views
Internal Twilio error for voice call StatusCallBack
I am encountering an internal Twilio error (https://i.sstatic.net/Gej46.png) when handling StatusCallBack Events. I have a function that is supposed to update the status of outgoing calls, but it ...
-1
votes
1
answer
177
views
Java TTS bot sounds robotic how to make it sounds more like a human?
I want to create a TTS bot in java and i using FreeTTS software to this and its sounds like a translator bot is there any option to change a voice speaker to kinda human voice or it is other software ...
- 11
0
votes
0
answers
165
views
Figuring out multiprocessing with RVC
Currently I am trying to find a way to make my script to launch a series of functions in parallel but errors keep coming up. At the moment I am using RVC-CLI, but I can change to original RVC repo and ...
1
vote
0
answers
168
views
agora_rtc_engine implementation for video and voice call within a chat module
What went wrong:
Running Gradle task 'assembleDebug'...
Execution failed for task ':agora_rtc_engine:buildCMakeDebug[arm64-v8a]'.
Running Gradle task 'assembleDebug'...
com.android.ide.common.process....
-3
votes
1
answer
173
views
How to change the voice recognition to french (always try to speak in english in twilio)
How to change the voice recognition to french (always try to speak in english in twilio). It work well in voiceflow but in twilio the system always try to make english word but I want it to make ...
- 11
-1
votes
1
answer
86
views
Python, Voice Assistant
I use "subprocess" to open a browser window using a voice assistant (in python). Actually, it opens. But how do I write code so that the browser closes with a certain command, for example, &...
1
vote
0
answers
925
views
how to create custom voice to be used for tts using a voice model?
Is it possible to use a voice model and then create a custom voice out of it to be used in SpeechSynthesis api? I have a tts app using that api, and I want to add custom voices.
I already tried to ...
0
votes
0
answers
146
views
ColdFusion - Vonage Inboud voice api call Answer Webhook CURL - issue with ncco object can't send multiple response to text to speech
I am successfully able to recive inboud call on my webhook and it works nicely i got the automated voice of below text it is working good. however i am getting "Unexpected content type: text/html;...
- 109
1
vote
1
answer
180
views
Discord.js code works fine while playing local files, while trying to play urls it doesn't play anything
const Discord = require('discord.js');
const { Client, GatewayIntentBits } = require('discord.js');
const client = new Client({ intents:
[
GatewayIntentBits.Guilds,
...
- 11
1
vote
1
answer
69
views
Using socket in Vxml and Voice browsers
I'm trying to link my backend with my vxml code and and frontend application (web-browser based). I want the backend to send out data to both my vxml application and web based one in sync.
So i came ...
1
vote
0
answers
40
views
PyAnnote Giving [Errno -9981] Input overflowed
I have 2 files that require me to record a voice sample. I'm trying to install a voice authentication library. I have successfully recorded voice samples to add my voice to the database. However, when ...
0
votes
0
answers
190
views
Error when using Speech Recognition Library at Pyhton
import pyttsx3
import speech_recognition as sr
def takecommand():
r = sr.Recognizer()
with sr.Microphone() as source:
print("Escuchando...")
r.pause_threshold = 1
...
0
votes
0
answers
1k
views
I'm having issues with installing tts-generation-webui
I'm new to using machine learning programs on Github, and decided to try my hand at machine learning by installing tts-generation-webui.
I followed the instructions as intended, installing the program ...
- 1
1
vote
0
answers
79
views
Female voice using MCI voice commands?
Can MCI voice control in VB6 produce a female voice using MCI voice commands?
It works fine now but only in a male's voice.
- 11
-2
votes
1
answer
156
views
Get recipient voice during call for AI callbot
I am working on the callbot.
What i need is to get the Realtime recipient's response (not complete call recording)
I am using Twilio for call.
Is there any way to get the Realtime response of ...