Local ElevenLabs Video Studio

Upload video, transcribe a segment, edit text, generate voice with settings + speed, then download audio or render video.
Backend: Node + ffmpeg · Secret: .env only
1) Video + Segment + Transcript No video
Start (sec)
End (sec)
Transcript (edit)
2) Voice + TTS Settings Voices not loaded
Voice quality controls
Stability 0.50
Similarity 0.75
Style 0.00
Speed 1.00x
3) Render video (replace audio)
Render keeps the original video track and replaces audio with your generated voice.