Articulate Storyline text to speech with your own AI voices
Storyline 360 has text to speech built in: Insert, Audio, Text-to-Speech turns a script into narration on the slide. It needs an internet connection and offers the voices of its own library, and Storyline 3 has no text to speech at all.
When you need a narrator that stays the same across all your courses, character voices for a branching scenario, a voice of your own, or narration made offline, voice the slides with the SuperClonica engine and add them to Storyline as ordinary audio files. This guide shows how.
When an outside voice makes sense
Use the built-in feature for quick drafts. An outside voice helps when a course series needs one recognizable narrator, when a scenario needs several characters, when the company wants narration in its own trainer’s voice, when you work without internet, or when you use Storyline 3, which has no text to speech.
Try a voice free
On any SuperClonica voice page, type a sentence of 30 to 100 characters from your course, choose the language and press Voice it. You can listen and download it in a few seconds, with no account, and compare narrators on your real script.
Voice every slide offline
Install the free engine with python -m pip install superclonica-cpu. Save the script of each slide as its own text file, for example slides/01.txt, slides/02.txt, and voice them all with one line: for f in slides/*.txt; do superclonica --text-file "$f" --voice F2 --lang en --output "${f%.txt}.wav"; done. Each slide gets a WAV file of the same name. The engine runs offline on an ordinary processor, with no character limit, and F2 can be replaced by any catalog voice file.
Add the audio in Storyline
Open the slide, go to the Insert tab, open the Audio menu and choose Audio from File. The clip appears on the slide’s timeline, where you sync it with animations as usual. To swap a built-in text-to-speech clip for your file, right-click it on the timeline and choose Replace Audio, then Audio from File. When the script changes, voice the edited text file again and replace that one clip.
Voices for courses
Calm narrators such as Pleasant Announcer and Business Male Voice suit explanations; the ten stock voices of the model, M1 to M5 and F1 to F5, are free in the engine; character voices liven up scenarios. A narrator in your own or a trainer’s voice can be made in the studio from a short recording, with that person’s consent, and trained on a computer with an NVIDIA graphics card.