Music for video editors, written to your edit
Published October 2026
A stock track is written for no picture in particular, so you cut the picture to the music or the music to the picture and hide the seams. Here the score is written to your locked cut: it starts and stops where the scenes do, its accents land on your cuts, it gets out of the way of the lines, and it comes back with the stems you need for the mix.
What changes for an editor
- No cutting music to length. Each cue is written to its scene's length, to the frame.
- Hits where you cut. Every cut is found frame-exact and the tempo bends so the big moments fall on a downbeat.
- Room for the dialogue. The music dips under every line on its own (about 14 dB on a test scene with five lines), and the dialogue is never processed.
- Mix-ready files. A 24-bit printmaster at your delivery loudness, an M&E, the dialogue / music / effects stems, every cue's mix and every instrument's stem.
- Temp music you can't clear? Replace it and keep the dialogue: the soundtrack is split first, the old music lifted out, the score written in its place.
What you get back
- The scored film: your picture, copied untouched, with the new soundtrack (MP4 with AAC 320k, or a MOV with 24-bit PCM if that is what you sent).
- The printmaster: the whole mix as a 24-bit, 48 kHz WAV, normalized to the delivery loudness you pick (web −16, streaming −14 or broadcast −23 LUFS) with the true peak under the limit.
- An M&E: music and effects without the dialogue, for a dub or a trailer.
- Dialogue, music and effects stems, when your film had a soundtrack of its own.
- Every cue's mix and every part as its own stem, with the notes it played, on a timeline you can keep editing.
- A Logic Pro or Ableton Live project of the whole score, one button from the studio.
Working with it
Export your cut (MP4 or MOV, up to 2 GB), drop it in the scoring studio, pick how much music you want (sparse, balanced or wall to wall) and the delivery loudness, and add a line of direction if you have one. A 27-second scene came back scored in about 7 minutes on the live service; a longer film takes longer, mostly in the performances. Then give notes per cue, like you would to a composer, and the film is delivered again with only that cue changed.
How it works
- Watch. It reads every frame: each cut to the frame, each shot's light, colour and motion, and where people talk. From that it proposes cues (1M1, 1M2 …) with SMPTE timecode in and out and the moments worth hitting.
- Listen. If the film already has a soundtrack, it splits it into dialogue, music and effects, so the score can replace the old music, re-orchestrate it, remix it or leave it alone, and the dialogue stays as it was.
- Write. An AI composer writes every part as notes, on a tempo map that lands the big moments on downbeats, thinner under the lines and bigger where the picture opens up.
- Perform. Instrument models trained on real recordings play every part, one stem each, and each part comes back with a check of whether it played its notes.
- Mix and deliver. Each cue is mixed in a hall, laid at its timecode, dipped under the dialogue and normalized to your delivery loudness, then put back on the picture.
What it costs
Watching the film, mixing and delivery are free. The performances use credits, like any render on Doseedo: 10 credits for every 30 seconds of music for each group of up to six parts, and a flat 20 to split the film's own soundtrack. A one-minute scene with a mid-size orchestra is usually 60 to 140 credits; the panel shows the estimate for your film before you start, beside what you have left.
A free account comes with 120 credits a month. Pro is $12 a month with 2,000. You own what you make, to the extent the law allows (Terms §6.3).
Honest limits
- Instrumental only. No songs, no vocals.
- Instrument models, not a session orchestra. They are trained on real recordings and each part is checked against its notes, but a live orchestra on a scoring stage is a different thing, and a picky ear will hear it on exposed solos.
- It sees the picture, not the plot. The composer reads the keyframes to decide what a scene is about; your direction is what tells it what matters.
- Long films are scored in up to eight cues per pass, the ones the picture needs most. Ask for more afterwards.
- Splitting a busy soundtrack is not perfect. When the old music is replaced, some of its percussion can stay in the effects, about 10 dB down.
Score your cut
Drop the locked cut, pick a sound, and get the scored film back with an M&E and every stem.
Open the scoring studio →FAQ
Can I get stems for the mix?
Yes: dialogue, music and effects stems, an M&E, each cue's mix and each instrument's stem, plus a 24-bit printmaster at the loudness you choose.
Will the music fit my cut exactly?
Each cue is written to its scene's timecode and the tempo map puts the important hits on downbeats, so there is nothing to trim.
What loudness does it deliver at?
Web −16, streaming −14 or broadcast −23 LUFS, with the true peak kept under the limit.
Can I replace my temp music?
Yes. The soundtrack is split into dialogue, music and effects, the temp music is removed and the new score is written in its place, with the dialogue untouched.
Does it work for documentaries and corporate video?
Yes. Pick Documentary or describe the tone; the music stays under the narration.
AI film scoring · an original score for your cut
- For editorsa score cut to your edit
- For directorsyour short, scored
- For composersyour parts, played
- For creatorsan original score, not stock
- Replace a film's musickeep the dialogue
- Score a silent filmwall to wall
- With your own AI agentthe same loop over MCP
- The demo reelone film per genre
- Big Buck Bunnyevery call and receipt
- AI tools comparedwhat each does with a cut
- Stock music comparedEpidemic, Artlist, ACE Studio …