Voice-over, transcription, sound effects and stem separation in one place. You see the price of every job before you run it.
Four working tools: voice-over, transcription, sound effects and stem separation.
Convert text to natural speech
Transcribe audio and video to text and SRT subtitles
Generate sound effects with AI
Split a song into vocals, drums, bass, guitar, piano and an accompaniment track
Music generation and voice cloning are paused: their models are licensed for non-commercial use only. They will return with new engines.
Start with the AI voice-over: type a text and hear it in one of 12 voices.
ElevenLabs v3 for speech and effects, Demucs for separation, Whisper for transcription.
The price is shown on the button before you start, and a failed job costs nothing.
Files go to the Pixelift server in the EU, and the AI models run at providers listed among our sub-processors (fal.ai, Replicate).
Choose one of four AI audio tools.
Type a text, upload a recording or describe a sound.
Play the result and download the file or the text.
Intros and announcements read by the voice-over, sound effects and an episode transcript.
Voice-over and sound effects for videos, SRT subtitles from a transcript.
Voice-over and transcription through the Pixelift API in your app.
Split songs into stems and make accompaniment tracks without vocals.
The audio tools require an account; new accounts get free credits to start.
Get started