If you have ever wondered why one voice effect feels like part of your own mouth while another sounds like a different person entirely, you have already noticed the split this page is about. The two families are built on different ideas, they cost different amounts of delay, and they are good at different jobs. If you want the broader picture of what a voice changer even is, start with what is a voice changer and come back.
Reshape versus replace
A DSP voice effect reshapes your voice. Pitch shifts, formant moves, robot and radio character, all of it is arithmetic applied to the signal coming out of your mic. Your timing, your phrasing, your laugh, they all survive the trip. The result is recognizably you, processed. Because it is arithmetic, most of the cost is nothing: an effect voice like Robot, Radio or Ghost adds no delay at all on top of your normal mic path. The pitch-based voices are the exception. Deep, Anime and Demon need a short analysis window, so Patchd bills them at 78 ms, Pop Star at 55 ms and Sprite at 25 ms, which is still a fraction of what AI conversion costs.
AI voice conversion replaces your voice. A trained model listens to what you say and produces the same words in a different voice, a wholly different character with its own timbre. You still drive the performance, but the sound that comes out is not a filtered version of you; it is a new voice wearing your delivery. That power has a price: the conversion adds about 245 ms of delay, plus a few seconds of one-time warm-up the first time you select an AI voice.
So the honest decision rule is short. If you are having a conversation, a chatty stream, a call, comms in a game, you want the DSP family: even its slowest pitch voice keeps the back-and-forth feeling natural. If you are doing a character bit, an alternate persona, a voice that needs to be genuinely somebody else, the AI family is the only one that can do it, and a quarter of a second is a fair trade for a whole new identity.
How the two families live together in Persona
In Persona, Patchd's voice changer, the two families are not two products or two modes. They sit in the same voice list and behave the same way from where you sit. Any voice, DSP or AI, can take its own hotkey bind, and a separate toggle turns Persona off and back on again, dropping you to your real, unprocessed voice and then returning you to your last voice, so leaving character mid-sentence is one keypress, not a menu dive.
When you jump between voices, the new voice fades in over about 10 ms from zero rather than arriving at full level, so it never clicks in. The one exception to instant switching is the first time you pick an AI voice in a session: the model loads once, which takes a few seconds, and after that warm-up switching to it is near-instant like everything else.
Persona also does not care where your voice comes from or where it goes. It runs on any input, inside the Patchd mixer as the last stage of a channel, and it has a face of its own, one click from the mixer, for when voice changing is all you are doing. On the Free tier you get 6 rotating taster voices to play with; the full library is 111 voices, including the AI voices, on Studio. If you are building a full stream chain around it, the streaming voice changer guide walks the whole setup.
Why the latency actually differs
The delay gap between the families is not an implementation detail someone could optimize away next quarter. It falls straight out of what each family is doing. A DSP effect is a fixed formula evaluated on every sample as it arrives:
y[n] = f(x[n])Every output sample is a formula applied to input samples the effect has already seen. At 48 kHz that formula runs 48,000 times a second and never falls behind. It is math with no opinions and no waiting room.
Because the formula needs nothing beyond the samples already in hand, an effect like a filter or modulation adds essentially zero delay of its own. What you hear is just the normal engine path: in Patchd that is about 10.7 ms through the bus at a 512 buffer, and smaller ASIO buffers take it lower. Pitch and formant shifting are the exception among DSP voices: they need a short window of audio to work on, so they add tens of milliseconds, still far below what AI conversion costs.
AI conversion cannot work per sample, because a single sample carries no meaning. The model needs a frame of audio, a chunk long enough to contain something worth converting, and then it needs time to run on that chunk. A trained model runs on every frame of audio, and that takes real compute. So the floor on its latency is structural:
latency >= frame_time + compute_timeThe conversion can never be faster than the frame it waits for plus the compute it spends. For Persona's AI voices those two terms add up to about 245 ms. You cannot convert audio you have not heard yet; physics has never once granted an exception.
Keep the two numbers separate, because they answer different questions. The 10.7 ms figure is the mixer's bus path, the trip every voice takes: most DSP voices add nothing on top of it, and the slowest add up to 103 ms. The roughly 245 ms figure is what an AI voice adds on top of whatever path it sits in. They do not average, and no amount of buffer tuning moves the AI number, because buffers are not where it lives. The few seconds of first-use warm-up is different again: that is the model loading once, not a per-word cost, which is why switching back to a warmed-up AI voice is near-instant. For the deeper arithmetic on all of this, see voice changer latency, explained.
Two families, one seat
The comparison ends somewhere pleasantly boring: you do not have to choose. In Patchd, Persona sits at the end of the channel after your cleanup chain, and the DSP voices and AI voices share the same list, the same per-voice hotkeys, and the same fade-in on every switch. Chat on an instant voice, hit one key for the character bit, hit the toggle to be yourself again. You can try it yourself: Patchd is in open beta now, and if you clear the terms your invitation arrives straight away.