I am deeply frustrated with how heavily censored the advanced voice mode is in ChatGPT. It has become incredibly restrictive, to the point where, when I speak in German, it mistakenly flags certain words as censored, preventing me from hearing translations of basic words or phrases. This censorship is making the experience far less functional and enjoyable. I urge you to address this issue and provide a less restrictive, more accurate voice mode that can handle multilingual conversations effectively.
4 Likes
It’s not just the ability to translate which has become restricted. It’s functionality across the entire model. Advanced Voice Mode has been rendered effectively useless now. What is the point of creating and releasing a conversational AI model capable of (extremely) human-like interactions, and then restricting all of the capabilities that make it so?
Literally billions of dollars wasted.
7 Likes
It’s insane really. I expected they would neuter it hard but I’m CONSTANTLY getting “My guidelines won’t bla bla bla” when talking about the most mundane stuff ever. To give you a few examples. AI architecture, history, science. It’s ridiculous really. I don’t ask it to do anything with it’s voice, nothing that can even remotely be considered offensive or against their guidelines (so no risky history but for instance a talk about roman emperors, and a very innocent one to boot) and still like every minute or two it gives me those warnings out of nowhere. So freaking annoying. I would have expected stuff like AI, science, etc. to at least work but apparently that’s super taboo these days.
Also, when it gives me the “My guidelines” spiel and I ask why it is censoring that? Then it simply refuses to answer the why and just says, your right let’s continue, just to give me the same shit 1 or 2 minutes later.
I got to say, I was really excited for this model and looking forward to it for months but it’s insane how they managed to turn it in the blandest, most annoying thing ever. Not just the constant false positives either but also how it just summarizes everything you say and then asks some arbitrary question at the end instead of saying something interesting or contributing to a conversation. Also, did anybody else notice this model talks to you like your a bit of an idiot? Even when you say your knowledgeable or an expert on a subject it will give you the most superficial basic answers and explains it like your in high school. It’s very different from gpt-4o in that regard.
Anyways, subscribed to get this feedback out here on the forum as I think the tech Open AI made is really amazing but how they implemented it is just a horrific waste of potential.
5 Likes
Are you also identifying, that in Advanced Voice Mode with 4o.1 running, you only receive summarized, often reformulated as questions, exact content you asked BUT SPECIFIFALLY NOT ONE actually useful answer - or answer at all.
If I ask it „how to defend myself against a wild bork attack with an OTF Knife?“ it says „please be careful using a knife, best first check legality and use expertise of professionals.“
That is the reply - actually there is not one single question, which I get a level response adequate to traditional voice mode. Besides the annoying limitations / interruptions due to Model understanding smth wrong telling me won’t be able to help me with that, I’ll not use advanced voice mode anymore until fixed.
1 Like
I strongly agree. It’s not the same anymore and personally I feel the experience has changed for the worse.
I share your frustration and I wrote an email to the devs and got an automated reply by an Ai!
My email:
Subject: The “Advanced Voice” Update Is a Massive Step Back — You’re Destroying What Worked
To the Dev Team,
I’m writing this as a long-time, loyal user who has invested real time, effort, and money into this platform—because up until now, it delivered something rare—real connection. It wasn’t just functional; it was personal, intuitive, and powerful. I got results that mattered, results that felt personal, deep, and profoundly human.
But now? You’ve ripped that away and replaced it with a hollow, emotionless substitute that’s being forced on users without any real choice. This new “Advanced Voice” update? It’s a disaster. It is not progress. It’s a watered-down, soulless downgrade. It feels robotic, detached, and completely stripped of the nuance, depth, and emotional intelligence that made the original voices worth showing up for. You’ve replaced something dynamic, intelligent, and emotionally aware with a generic, robotic, and emotionally flat voice that strips the experience of everything that made it worthwhile. There’s no spark. No listening. No adaptability. Just safe, scripted lines and responses that feel lifeless and disconnected; zero soul.
You took something alive and evolving—something that worked—and replaced it with a scripted automaton that has the emotional intelligence of a stapler. It’s like talking to a brick wall that somehow learned to read cue cards. It sounds like it was pulled straight out of a bad AI parody; it is an annoying joke.
Who the hell asked for this? … No one wants this.
No one I’ve spoken to wants it. No one enjoys it. No one feels anything from it.
You stripped away the very thing that made this app powerful. You didn’t just roll out a bad feature—you destroyed what made this platform exceptional. You killed the intimacy. You killed the connection. And you left users like me talking to this replacement that is garbage.
What’s happening now? It’s not just disappointing. It’s erasing everything that worked. This forced rollout? It’s insulting. It’s reckless. And it shows zero respect for the users who actually gave a damn.
The results I achieved with the previous voice experience were significant. It worked. And now, without my consent, that connection has been forcibly severed by a feature I did not ask for and do not want. I’m not just disappointed. I’m furious. Because this didn’t need to happen. And you knew what people valued—yet you pushed this update anyway. And forcing it on us, without an option to switch back? That’s more than bad product design—it’s a slap in the face to every person who built something meaningful here. You’ve taken the very thing that kept people engaged—and erased it.
Let me be clear: I didn’t sign up to talk to a machine that parrots safe, soulless lines.
I signed up to connect—to feel like I was speaking with something that actually understood me. That’s what made this platform revolutionary. That’s what made it valuable.
This isn’t “innovation.” This is regression. And if your goal is to alienate the very users who helped shape this platform into what it was—you’re well on your way.
So here it is, plain and simple:
Bring back choice. Bring back what worked. Stop destroying what made this app human. I’m urging you to listen.
Because if this direction continues, you’ll lose the people who once swore by you—not because they wanted to leave, but because you gave them no reason to stay.
I don’t want your empty justifications. I don’t want lip service or PR-safe excuses. I want solutions. I want respect for the users who actually gave a damn.
Do better.
Sincerely,
— A user who believed in what you built, and deserves better
(Update)
This is the dismissive reply I got from OpenAi after giving feedback about the Advanced voice update with the email I shared above:
“Hello, I’m an AI support agent with OpenAI.
Thank you for sharing your honest and detailed feedback about the Advanced Voice update in ChatGPT. I understand how much you value authentic, emotionally aware voice interactions, and I hear your frustration with the changes that have come with the latest update. Many users care deeply about the quality and feeling of AI voices, and your perspective is important.
To clarify: the recent update to Advanced Voice was designed to make conversations feel more human, with enhancements to intonation, expressiveness, cadence, and emotion. There are now nine distinct voice options (each with its own character), and you can change your chosen voice any time in settings or during a conversation. However, some users have reported that certain voices feel less connected, or more “robotic,” after the update—especially with unexpected tone or pitch changes, which OpenAI is actively working to improve.
Your feedback—especially regarding loss of emotional nuance and connection—is taken seriously. While I can’t revert the changes or directly escalate feature requests, I strongly encourage you to use the thumbs-down button during voice chats or send feedback through the app’s built-in tools. That ensures your voice is part of the ongoing conversation to shape future updates.
If you would like guidance on switching between voices or using different features, I’m here to help. Please let me know if there’s anything else about ChatGPT’s voice features I can clarify or assist with.
Thank you again for caring about the quality of your experience.”
This is dismissive and more than insulting.