Create an older fictional character with three voice effects. Start from a reflective grandpa, grumpy neighbor or storyteller, then adjust the sound.
Guests can generate up to 500 text characters per day. No sign-up or credit card required. See free and paid allowances.
Add an effect to up to 30 seconds of your recording. Your file stays in this browser; no generation credits are used.
Free audio is for personal, non-commercial use. Commercial use is included on all paid plans, including Starter, subject to the Terms and your rights to the content and voice.
Listen before you create
Compare three original lines with the grandpa, neighbor and storyteller effects applied. Listening uses no credits.
English · adjustable voice effect
Charles generated at 1× before this effect was applied. Compare the original below; pitch-and-pace processing can change duration.
“I remember when this road ended at the river. We took our time and noticed more along the way.”
Before · original AI voice
“I remember when this road ended at the river. We took our time and noticed more along the way.”
English · adjustable voice effect
Benjamin generated at 1× before this effect was applied. Compare the original below; pitch-and-pace processing can change duration.
“Another drone in my garden! At least this one remembered to bring its owner.”
Before · original AI voice
“Another drone in my garden! At least this one remembered to bring its owner.”
English · adjustable voice effect
Alex generated at 1× before this effect was applied. Compare the original below; pitch-and-pace processing can change duration.
“The lantern went out at the old bridge. Then we heard someone call from the other side.”
Before · original AI voice
“The lantern went out at the old bridge. Then we heard someone call from the other side.”
These are synthetic male voices with audio effects. They demonstrate fictional character treatments, not verified speaker ages or an imitation of a real person.
01
An older fictional character is more convincing when the writing gives them a point of view. Decide what they remember, what they notice and what they want from the person listening. A reflective narrator might pause to describe an overlooked detail, while an impatient neighbor may get straight to a complaint. Pitch alone does not establish age, and older people do not all speak with the same rhythm or timbre. Use the presets on this page as sound-design starting points for an original character. They apply real audio processing to a selected synthetic voice; they do not estimate a speaker's age or recreate a particular grandparent, actor or public figure.
02
Try the three styles with a short line before committing to a longer scene. The grandpa setting is intended for a reflective character, the neighbor setting for a more pointed reply, and the storyteller setting for narration. Each starts from a real English voice and an explicit speaking-speed choice. Listen to both the original generated audio and the processed version, then reduce the effect strength if the treatment obscures consonants. The names describe creative uses rather than verified ages or personalities. A useful setting is the one that fits your line while keeping its meaning clear. Save the voice, speed, effect and strength with the script so later clips can start from the same configuration.
03
A character recalling the past needs something concrete to remember. A road that once ended at the river, the sound of a workshop door or a familiar routine gives the listener a place to imagine. Those details are usually more useful than repeatedly announcing that the character is old. Keep the memory connected to the current scene: what does the listener learn, and why is this person telling it now? Avoid making every sentence a joke about age or a stock phrase. An original, respectful character can be funny, frustrated, confident or uncertain without relying on a stereotype. Generate only the spoken words and keep stage directions in your separate production notes.
04
The extra pitch-and-pace adjustment changes playback pitch and duration together. Moving it downward can make a clip lower and longer; moving it upward can make it higher and shorter. It is not independent pitch correction that preserves the original length. Start close to the default and listen for reduced clarity, especially at the ends of words. Effect strength controls the amount of processing blended into the sound. The effect can be adjusted on an existing result without asking the voice model to read the text again. If the underlying pronunciation is wrong, however, processing will not reliably repair it. Correct the script and generate a new reading only when the spoken content needs to change.
05
For a precise pause, sigh or interruption, record the performance yourself and use Upload or record audio to apply the older-character treatment locally. In that workflow the effect works as an elderly voice changer for your own short clip. The pitch-and-pace shift can still change the clip length, so compare the processed output with your original timing. If you also want to change the speaker timbre, the separate converter can use an authorized target reference, but it does not guarantee that every breath or word will remain unchanged. Do not use a relative's private recordings as a reference without explicit permission. A fictional performance should be presented as such, especially when the listener might otherwise believe a real person is speaking. If you need fine control over a particular gesture or emotion, treat the generated line as a draft and keep the option of a directed human performance.
06
Create one speaker's line at a time within the 500-character request limit. Leave scene labels out of the spoken text, and download each useful take with a descriptive filename. Place the dialogue in your editor before adding room tone, music or sound effects. A voice that sounds clear alone may become difficult to understand under a busy soundtrack, so check the full mix at ordinary volume. Listen on a small speaker as well as headphones. The local character processing is a sound-design tool, not a guarantee of realism, anonymity or a particular age. Choose the lightest treatment that communicates the role while preserving the words your audience needs to hear.
A little clarity
The details that help you create with confidence.
Contact us →Choose one of the three older-character styles to apply pitch, filtering and texture to a real male voice. Tune strength and pitch with pace after generation. The result is a fictional treatment, not an age estimate or a guaranteed elderly performance.
Guests can use 500 characters a day, shared between standard speech and instant cloning. Signed-in users use their displayed credits. Listening to existing samples uses no credits.
Yes. Choose Upload or record audio to apply these effects to up to 30 seconds of your recording locally, without generation credits. For a different speaker timbre guided by a reference, use the separate voice converter.
Some styles add a subtle pulsing texture through audio processing, alongside pitch and filtering. There are no independent rasp or breathiness sliders, and the effect does not guarantee biological aging or a specific acting performance.
Only if the speaker has given explicit permission and you have the necessary rights. Do not use family recordings to impersonate a relative or imply they said something they did not.