Mimicore user guide
Everything you need to go from download to talking, streaming and creating in any voice.
- 1. Install and first start
- 2. Set up the virtual microphone
- 3. Go live
- 4. Your voices
- 5. Voice effects
- 6. Speak: text to speech
- 7. Dub a video
- 8. Soundboard
- 9. Hotkeys and push-to-talk
- 10. Settings
- 11. Use cases: step-by-step recipes
- 12. Troubleshooting
- 13. Privacy and responsible use
1. Install and first start
- Download Mimicore-setup.exe from the download page (you agree to the terms there) and run it. It installs for your Windows user only and needs no admin rights.
- If Windows shows "Windows protected your PC", click More info › Run anyway. Mimicore is new and not yet code-signed; every update is still signed and verified by the app.
- The app shows no terms screen: you accept the terms once, on the download page, before the installer downloads. You must be 18 or older and clone only your own voice or voices you have permission to use.
- Pick what to install: Instant voice cloning (clone a voice from 10–20 seconds, 23 languages, also powers Speak and Dub) and Trained voices (RVC) (use voices you trained or imported, lowest delay). Mimicore chooses the model size that suits your PC (about 1 to 2 GB for instant cloning, 0.3 GB for trained voices), downloads it, then tunes itself to your PC: it runs both engines for a few seconds and stores what your PC can keep smooth. Strong PCs start at the best quality, weak PCs at a lighter but still good setting. Dubbing and Voice Training are optional add-ons later in Settings.
- Sign in with Google, Discord or email. It is free: 20 minutes of live voice every day. To try Live or Studio, start a 7-day free trial from your account page (a refundable INR 2 / USD 1 check of your payment method; billing starts after the trial; cancel any time before).
- A tour of every page (Live, Speak, Dub, Voices, Soundboard, Support, Settings) shows where everything is. After each update that changes the interface, a short What's new tour shows only what changed. Press Esc to skip a tour. The 28 voice effects work right away, even before a model finishes downloading.
2. Set up the virtual microphone
The virtual microphone lets Discord, Zoom, OBS and games hear your changed voice. You set it up once.
- Open Live › Output › Set up virtual mic. Mimicore downloads the free VB-CABLE driver from vb-audio.com, checks its signature and installs it. Click Yes when Windows asks.
- If Windows asks for a restart, restart and open Mimicore again. The cable is selected automatically.
- In the other app, choose CABLE Output (VB-Audio Virtual Cable) as the microphone:
- Discord: User Settings › Voice & Video › Input Device. Turn off Discord's own Noise Suppression (Krisp) and Echo Cancellation, because they fight the changed voice.
- OBS: add an Audio Input Capture source and select CABLE Output.
- Zoom / Teams / Meet: Settings › Audio › Microphone.
- Games: set the in-game voice input device. If the game has no choice, set CABLE Output as the Windows default recording device.
- Turn on Hear myself to listen to your new voice. Use headphones so the microphone doesn't pick up the speakers.
3. Go live
- On Live, pick a voice or effect from the list and press the big Start button.
- Speak. The status line shows the delay, the processing time per block and any glitches.
- Instant voices have a Quality switch. Auto (the default) uses what the benchmark found and keeps adjusting while you talk; the manual choices are below:
- Lite (about 0.5 to 1.4 s, adapts to your PC): for slower PCs and integrated graphics. It is selected automatically on a PC without a graphics card of 3 GB or more, and Mimicore steps down to a lighter quality by itself if the voice cannot keep up.
- Low (about 0.35 s): quickest reaction, for gaming. Drawback: a slightly less polished sound.
- Medium (about 0.45 s): a good balance of reaction and quality.
- High (about 0.5 s): most natural and stable, for streams and recordings. Drawback: the highest delay of the three.
- Trained voices have the same Quality switch:
- Auto: tuned to your PC for the lowest delay it can sustain (about 0.3 s on a mid-range GPU). Drawback: the delay can change a little when it adjusts.
- Low (about 0.3 s): the lowest delay, great for gaming and calls. Drawback: the most work for your PC, so it can stutter on a busy or weak one.
- Medium (about 0.5 s): balanced, steadier with less load. Drawback: a slower reaction than Low.
- High (about 0.7 s): the smoothest and most stable sound with the least load on your PC, good for streaming and recording. Drawback: the highest delay.
- Self-healing: while you talk, Mimicore watches how long each block takes and whether the sound glitches. If your PC cannot keep up (a game starts, the laptop throttles) it moves to a lighter setting within seconds and says so; after a long calm stretch it moves back up. The Live engine panel under the stage shows it live: block time against block length, CPU (the main load of instant voices) and GPU (the main load of trained voices), video memory, glitches, delay, the current step and how often it adjusted.
- Tune for this PC (Settings › Add-ons) re-runs the benchmark any time: after a hardware or driver change, or if a voice stutters. Thorough test measures more steps. Stop the live voice first.
Controls on the Live page:
- Mute silences your microphone without stopping the voice, so unmuting is instant.
- Original-voice test (bypass) passes your real voice through, to check levels.
- Add an effect layers any effect on top of your voice: radio, cave, robot and more.
- Noise suppression removes background noise (on by default).
- Automatic level makes quiet microphones louder (on by default).
- Noise gate (Off / Light / Medium / Strong) silences everything between your words: keyboard, fan, breathing.
- Voice tuning (trained voices only) has Pitch (in semitones; +12 is one octave up) and Voice strength (how strongly the sound is pulled toward the trained voice). Both apply instantly.
- 🎯 Calibrate to my voice (trained voices only): read one sentence and Mimicore measures your pitch and your room. It then sets the pitch and noise gate for the closest match. The settings are saved for that voice and load whenever you pick it.
If the status shows Struggling, your PC can't keep up right now. Mimicore lowers the setting by itself; you can also close other programs that use the graphics card or run Tune for this PC again.
4. Your voices
Open Voices & effects.
Instant voice (10–20 seconds)
- Click + Instant voice and give the voice a name.
- Record about 15–20 seconds of natural, continuous speech in a quiet room, or import a clean recording. Background noise is removed automatically.
- Click Create voice. It's ready in under a minute and works live, in Speak and in Dub.
Voice gallery
Click Get the voice gallery (27 MB) once, then press ▶ to hear the voices and Add to my voices to use one. There are 19 original voices, and each is a blend of two speakers, so none copies a real person.
Mix voices
Mix voices… blends two of your instant voices into a brand-new voice. Move the slider between A and B and press Create mix. It's great for characters and for a voice that is yours alone.
Train a voice (closest likeness)
Training makes the most faithful copy of a voice from 10–30 minutes of clean recordings of one person.
- On this PC needs an NVIDIA graphics card (GTX 16 / RTX 20 series or newer, 4 GB+). Install the Voice Training add-on when asked, add your recordings, choose a quality and click Start training:
- Quick test: about 10–20 minutes.
- Good (recommended): about 25–50 minutes.
- Best: about 1–2 hours.
- Cloud (free) works on any PC. It trains on a free Google Colab GPU in your own Google account, with the same trainer and the same quality:
- Click Connect Google Drive and allow access. Mimicore can see only the files it creates.
- Add your recordings, choose a quality and click Upload & open Colab.
- In the Colab tab, press ▶, click Run anyway, and allow Google Drive access.
- Keep the Colab tab open. Mimicore shows the progress and installs the voice automatically when it's done. The recordings are then moved to your Drive trash, unless you chose to keep them.
You can also start cloud training from the website.
Import RVC voices
Import RVC voices… adds existing RVC v2 voices (a folder with .pth/.onnx and .index) that you have the rights to use.
Other actions
- ▶ Preview plays a sample.
- Convert a file… turns a recording into that voice.
- Rename and Delete manage the voice.
5. Voice effects
28 classic effects (Robot, Demon, Chipmunk, Radio, Cave, Cathedral, 8-bit and more) run instantly on the CPU. They're free with no time limit.
- Press ▶ to hear an effect, then Use to pick it for Live.
- Apply to a file processes a recording.
- To layer an effect on top of a cloned or trained voice, use Live › Add an effect.
6. Speak: text to speech
- Type or paste text, or load a
.txtfile. - Pick a voice and a language (23 languages, including Hindi, Spanish, Japanese, Arabic and Chinese).
- Adjust Emotion and Variation if you like.
- Choose where it goes:
- Speak now plays it on your speakers and/or the virtual microphone, so people in your call hear it. A copy is saved.
- Save to file renders a WAV.
Trained voices speak through the default voice, converted with the pitch matched automatically. Files are marked as AI-generated in their metadata.
7. Dub a video
Turn a video's speech into another language, spoken in your voice. It runs fully offline.
- Install the free Dubbing add-on (Settings › Models & add-ons, about 3.2 GB) once.
- Open Dub a video, choose a file (MP4, MOV, MKV, M4A, MP3 or WAV), the spoken language (or Detect automatically), the target language and a voice.
- Set Original audio: keep some of the original under the dub for music and background sounds, or remove it for a clean voice track.
- Click Dub it. Mimicore transcribes, translates sentence by sentence, speaks each line in your voice and fits each line to its original timing.
- You get a WAV audio track and an SRT subtitle file. Put the audio on the video in any editor (CapCut, Premiere, DaVinci Resolve, Clipchamp) and add the subtitles if you like.
Dub only content you have the rights to.
8. Soundboard
- Air horn, applause, drum roll, sad trombone and more are built in.
- Add sounds to bring in your own clips: MP3, WAV, OGG, FLAC or M4A up to 5 minutes, as many as you like.
- Click a tile to play it into the virtual microphone. Turn on Also play on my speakers to hear it yourself.
- Give each sound a hotkey, set volumes in Edit, and drag tiles to reorder them.
- Sounds play even when the live voice is off.
9. Hotkeys and push-to-talk
Settings › Hotkeys. Click a box, then press a key or combination. Hotkeys work while a game or another app has focus.
| Action | What it does |
|---|---|
| Start / stop the live voice | Toggle the voice changer |
| Push-to-talk (hold) | When set, your mic is silent unless you hold this key |
| Mute / unmute microphone | Toggle mute |
| Original voice on / off | Toggle the bypass |
| Next / previous voice or effect | Cycle through your voices and effects |
| Switch straight to a voice | One key per favourite voice (its calibration comes with it) |
| Stop all soundboard sounds | Silence the soundboard |
Use combinations (Ctrl + Alt + …) or keys you don't use elsewhere (F7–F12, numpad): a bound key is reserved for Mimicore while it runs. A short tone confirms each hotkey; you can turn it off.
10. Settings
Settings has six tabs: Account, Hotkeys, Add-ons, General (theme, language, graphics card, window), Privacy & data (data folder, error reports, support info, export or delete your account) and About (updates, licenses).
- Add-ons are optional downloads, each with a "why" and a "skip it if":
- Live voice engines: Instant voice cloning (powers Speak, instant cloning and live conversion of a cloned voice; Mimicore picks the model size for your PC) and Trained voices (RVC) (0.3 GB, runs trained or imported voices live). "Advanced: model tiers" lists the Fast, Balanced and Ultra model files for people who want to manage them.
- Tune for this PC: your hardware class, what the benchmark chose for each engine, a Run benchmark and a Thorough test button and a table of the last test.
- Voice training (2.5 GB, NVIDIA only) lets this PC train RVC voices. No NVIDIA card? Use free cloud training instead.
- Video dubbing (about 3 GB): translates a video's speech into your voice in another language, offline.
- Cloud training (optional): connect your Google Drive to train on a free Google GPU.
- Account: your plan (Free, Live, Studio or Studio Lifetime, with a "trial" tag during a free trial), See plans, sign out.
- Free plan: 20 live minutes a day, short Speak / Dub / conversion clips (30 s), no cloning, mixing, importing or training.
- Always free: effects, the soundboard, the gallery and built-in voices.
- Live (monthly, annual or lifetime): unlimited live voice changing with built-in and gallery voices.
- Studio (monthly, annual or lifetime): everything unlimited, including your own voices live, cloning, mixing, importing, training, Speak and Dub.
- Hotkeys: see section 9.
- Models & add-ons: the two live engines, the PC benchmark, Voice Training and Dubbing.
- Appearance & language: dark, light or match Windows. The interface is available in English, हिन्दी, Español, Português, Français, Deutsch, Русский, 日本語 and Bahasa Indonesia.
- Updates: Mimicore checks automatically and can download updates in the background. You choose when to restart.
- Processing: pick the graphics card. Any DirectX 12 card works: NVIDIA, AMD or Intel.
- Cloud training: see which Google account is connected, or disconnect it.
- Your data: open the data folder, and optionally Send error reports (off by default; never includes audio, voices or text).
11. Use cases: step-by-step recipes
Gaming with friends on Discord
- Set up the virtual mic (section 2) and select CABLE Output in Discord.
- Pick a voice (an instant voice on Low quality, a trained voice, or an effect) and press Start.
- Set a Push-to-talk key and a Start / stop hotkey.
- Add soundboard clips with hotkeys for instant reactions.
Streaming and VTubing with OBS
- In OBS, add Audio Input Capture › CABLE Output.
- Bind Switch straight to a voice hotkeys for each character, plus Mute.
- Use Add an effect (Radio, Cave, Robot) for scenes, and the soundboard for alerts and memes.
Localise your YouTube videos and Shorts
- Clone your own voice (an instant voice, or train one for the closest likeness).
- Dub a video into Hindi, Spanish, Portuguese and more, all in your own voice.
- Replace the audio track in your editor and upload the SRT as subtitles.
Voiceovers, narration and audiobooks
- Install the Ultra tier for the most polished speech.
- In Speak, paste your script, pick your voice and language, and choose Save to file.
- Long texts are rendered sentence by sentence.
Private, anonymous calls
- Pick a gallery voice or a mix, so the voice belongs to no real person.
- Select CABLE Output in Zoom, Teams or Discord.
- Turn on noise suppression and a Light noise gate for a clean sound.
Role-play, D&D and characters
- Create characters with the mixer and effects (Giant, Ghost, Elf, Dark Lord…).
- Bind one hotkey per character and switch mid-sentence.
Your own voice, typed
For people who can't speak at times (illness, a sore throat, quiet places): record an instant voice while you can. Speak then reads typed text aloud in your own voice, live into a call.
Speak another language in your own voice
Type in Spanish, Japanese or Hindi in Speak. Your cloned voice says it with natural pronunciation, which is great for presentations and practice.
12. Support: the assistant, tickets and early builds
The Support tab (sign in first) is an assistant that knows the whole app and website. Ask anything: setup, voices, plans, errors.
- If it can solve it, it answers with the exact steps and a link to the guide.
- If it can't, it creates a support ticket for you (Talk to a person does this on request). You get an email at every step: received, confirmed as a real defect, fix in progress, a test build ready, resolved.
- Report a bug: type what you did and roughly when it happened, then press Report a bug. Mimicore picks the matching part of its local log (it records the pages and buttons you used, never what you type), removes your Windows user name and email addresses, and shows you what it would attach. Nothing is sent until you press Send ticket with log (or Send without log).
- Your tickets are listed at the top with their status. When a fix is ready you are emailed a link to an early build, or open Settings › Updates › Check for early release. Early builds are never installed automatically. Try what went wrong and press It is fixed or Still broken.
- Deleting your account deletes your tickets, chats and logs.
13. Troubleshooting
| Problem | Fix |
|---|---|
| Others can't hear me | Check that the voice is started, the Output › Virtual mic isn't Off, and the other app's microphone is CABLE Output. |
| I hear an echo or howling | Use headphones, or turn off Hear myself. |
| The voice sounds robotic or glitchy | Mimicore lowers the setting by itself. Also close other apps that use the graphics card, run Tune for this PC in Settings › Add-ons, and check that Settings › General › Processing uses your best card. |
| Too much delay | Use Low quality; trained voices have the lowest delay. Bluetooth headsets add their own delay, so wired is better. |
| My mic is too quiet | Keep Automatic level on, or raise the mic level in Windows sound settings. Calibrate shows warnings for quiet or clipping mics. |
| Keyboard or fan noise comes through | Turn on Noise suppression and set the Noise gate to Medium. |
| Training is greyed out | Training on the PC needs an NVIDIA card. Use Cloud (free) instead. |
| Colab says no GPU is available | Free GPUs are limited at busy times. Try again later; training continues from the last checkpoint. |
| The virtual mic doesn't appear | Restart Windows after the VB-CABLE install, then open Mimicore again. |
| "Used today's free live minutes" | Free live minutes refill every day. Live or Studio removes the limit. |
| "This PC isn't linked to your Studio plan" | Studio works on up to 2 PCs. Open Settings › Account › Your PCs (or the website account page), remove a PC you no longer use, then press Refresh. A removed PC can't be used with the account again. |
| "…is part of Studio" | Cloning, mixing, importing, training and long Speak / Dub clips need Studio (or a Studio free trial, start it on your account page). |
| Something else | Ask the Support tab: it answers or opens a ticket for you. Or Settings › Your data › Copy support info copies versions, graphics card, key settings and the last log lines (no personal data) to paste into your message. Open data folder has the full logs (logs\mimicore.log). The support email is on the website's contact page. |
14. Privacy and responsible use
- Your voice, your device, your cloud. Never ours. Live voice, cloning, effects, speech, dubbing and training on your PC all run locally. Microphone audio is processed in memory and never stored or sent.
- Optional cloud training uses only your own Google Drive and Colab. Mimicore can see only the files it creates there.
- The Support assistant sends what you type to our server and an AI provider; do not type passwords or payment details. Tickets (conversation plus a log you approve) are kept until you delete your account. We otherwise store only your account email and plan. Error reports are off unless you turn them on.
- Clone only your own voice or voices you have permission to use. Never use a cloned voice to deceive, defraud or impersonate anyone. Generated files are marked as AI-generated.
- Full texts: Acceptable Use · License · Privacy.