Pictory voiceover: AI voices or your own
Pictory turns scripts, articles and long videos into short videos with stock footage, captions and an AI voiceover. Its voice options depend on the plan, and the minutes are limited, so many creators make the voiceover elsewhere and add it to Pictory.
This guide sums up Pictory’s plans and voice options according to its pricing page, and shows how to make a voiceover for free with SuperClonica in a voice and language Pictory may not offer on your plan.
Plans and minutes
On its pricing page in October 2026, Starter costs $29 a month, or $25 billed yearly, with 30 minutes of video a month; Professional costs $59, or $35 yearly, with 90 minutes; Teams costs $199, or $119 yearly, with 300 minutes. The 14-day free trial includes 300 credits for up to 10 minutes, 3 video projects and 720p export with Pictory branding.
Voices in Pictory
Pictory includes ElevenLabs voices on every plan, including the trial. Starter supports 7 languages, while Professional and Teams support 29, and voice clones are listed from Professional. The voice features also cover your own voiceover, so you can bring audio made elsewhere.
Make your own voiceover offline
Install the free SuperClonica engine with python -m pip install superclonica-cpu, save the script as a text file and run superclonica --text-file script.txt --voice narrator.json --lang en --normalize --output voiceover.mp3. It runs offline on an ordinary processor with no character limit, in 31 languages on any plan you have with Pictory, and --normalize keeps every video at the same loudness. Then add the file in Pictory as your voiceover.
Keep the scenes in sync
Pictory splits a script into scenes. Voice the script scene by scene if you want to fine-tune the timing, or voice it in one piece and adjust scene durations to the audio. Write numbers and abbreviations the way they should sound, and keep sentences short for captions.
Pick a voice or use your own
Hear catalog narrators and announcers free on their pages: paste 30 to 100 characters, no account needed. Ten stock voices, M1 to M5 and F1 to F5, come with the engine and can be used commercially within the OpenRAIL-M model license. For your own voice, record a clean phrase of 5 to 10 seconds and train it in the studio; training on your own NVIDIA graphics card is free.