Podcasters
Turn an episode clip into a video for YouTube or Shorts.
Add a narration, a podcast clip or a voice actor's take instead of a script. Vid Optimus writes out what you said, cuts it into scenes that line up with your recording, then builds the visuals and captions around it. Your voice is what plays, at your own pace.
Text-to-speech is quick, but nothing sounds like you. On the Script screen, choose Use a voiceover and pick your audio file. Vid Optimus transcribes it with Groq, OpenAI or Deepgram using your own key, so you get the words and exactly when each one was said.
You check the transcript, fix any word it misheard, and join or split scenes where you like. The recording is then cut into scenes on its own timings, and AI Director plans the visuals over your real pacing.
Pick Deepgram under Transcribe with, beside Groq and OpenAI Whisper, with its Nova-3 or Nova-2 model. It times captions and reads your recording as Whisper does. The Spoken language list shows only the languages the chosen service can transcribe, and Mixed languages handles a recording that switches between them. A new Deepgram account comes with $200 of free credit and needs no credit card.
The transcript is yours to correct before anything is built. Change a misheard name, then join two scenes or split one in two where the story turns.
Because the timing comes from your recording, every caption word and every cut follows your real delivery, pauses and all. Nothing is stretched to fit a robot voice.
If you also have your own images and clips, SceneSync lines them up with your recording: changing picture in your pauses, at exact times you set, or from a scene sheet it writes for you.
See SceneSyncOn the Script screen, choose Use a voiceover, select the file, set the service and spoken language, then press Transcribe.
Fix any misheard word, then join or split scenes.
AI Director plans shots on your timing, or pick visuals by hand.
Your recording plays as it is, with captions, music and your visuals.
Turn an episode clip into a video for YouTube or Shorts.
Your performance stays exactly as recorded.
Record a lesson once and get a video with visuals and captions.
Straight answers about how it works and what it costs.
Since 3.0, a stretch too long for one scene is cut where the speaker pauses, so a recording with little punctuation, as Urdu often comes back from transcription, no longer becomes one scene minutes long.
Yes. Doodle Maker starts from a script or your own recording, and plans every drawing on your own timing.
MP3, WAV, M4A, AAC, OGG, FLAC, Opus or WMA.
Yes, a Groq key (free tier available), an OpenAI key or a Deepgram key (a new account comes with $200 of free credit) to transcribe the recording. Since 2.6 transcription is its own choice, so you can plan with OpenAI and transcribe with Groq's Whisper, or the other way round. No voice key is needed, because no AI voice is generated.
Yes. A Spoken language list sits under Transcribe with, and shows only the languages the chosen service can transcribe, including Urdu, Hindi and Arabic. Auto-detect is the default; naming the language stops it guessing wrong from a short or accented opening. Mixed languages handles a recording that switches between them.
Fix it in the transcript before the scenes are cut. Captions follow your corrected text.
No. It is cut into scenes for planning, but what plays in the video is your own recording, at your own pace.
With Use a voiceover, Vid Optimus builds the visuals for you. SceneSync is for when you already have your own images and clips and want them lined up with your audio.
Yes. Music ducks under your voice, and you can add an opening hook, a colour look and everything else on the timeline.
Free for 7 days with every feature. No card needed. Works on Windows and macOS.