Voicelify | Sailgio

Voice identity

Voice Clone

Use your saved voice clone

Make Voicelify speak with your own saved voice identity instead of a standard voice.

READY

Add a voice clone Unlock Voice Clone

Action

Choose what you want to generate

Source

For this mode, you can generate AI voice from timed text only, or combine it with a local source audio depending on the final audio result you want.

Text

0 / 50

Correct format: [00:00:01.240 - 00:00:03.980] Hello world

Invalid timed text format. Example: [00:00:01.240 - 00:00:03.980] Hello world

Audio source

Needed only if the final result keeps the original voice or background sounds.

Audio URL

Use a direct audio link or a supported media page handled by yt-dlp.

Choose source audio No file selected

Video source Free mode: videos under 1 minute.

Video URL

Choose a local video No file selected

Choose either a video URL or a local video.

Language and subtitles

Original language

Output language

Output language is required.

Include timestamps

Final audio result

Quick presets

AI voice + original background AI voice + background, no original voice Dubbed over original AI voice + full original audio AI voice only Only AI voice, no original sound Original full audio Original voice + background, no AI voice Original voice only Only original voice, no AI voice, no background Background only Only music and ambient sounds, no voices

Advanced audio layers

Keep AI voice Keep original voice Keep background sounds

Use a preset above, or manually fine-tune the audio layers.

AI voice settings

For now, Voicelify generates one AI voice per job. Multi-voice generation is coming soon.

Voice type

Emotion

Style

Voice clone Pro/VIP required

Use my saved voice clone

No saved voice clone found. Add your reference voice in your member area to unlock this option.

Voice

Output options

Output resolution

You can keep the source resolution or downgrade it to reduce cost. Upscaling is not supported, so a source cannot be rendered above its original resolution.

Audio mix levels

AI voice level 100%

Raise or soften the generated voice in the final mix.

Original audio level 100%

Useful when the AI voice is layered over the original voice or source soundtrack.

Voice speed

Playback speed 100%

Speeds up or slows down the generated AI voice after synthesis. 100% keeps the original speed.

Subtitle style

Choose a preset for quick readability, or switch to custom colors.

Text color

Background color

Subtitle position

Workspace output

Ready for generation

Your audio, video or transcript will appear here once the job is completed.

Waiting...

Download

No need to reload the page to start a new conversion.