Eddie AI

Feature · Speaker identification

The most advanced speaker identification AI in the world

Eddie hears who is talking and sees who is on camera.

Two cameras, Maya and Jon, with Eddie marking “Maya is speaking” on the voice lanes

Voice and face

Two ways to know who is talking

Two speakers found: Maya and Jon, each on their own waveform lane

Aural

Eddie hears who is talking

Every line labelled by speaker. Rename, move or merge, and the fix reaches every angle.

Visual

Eddie sees who is talking

On a multicam shoot, the voice that moves a visible mouth names that camera.

  1. 01First passReads mouth movement while each speaker talks.
  2. 02Second lookWatches lips against the audio. Names both in a two-shot.
  3. 03Clear matches onlyUnsure? Eddie leaves it unlabelled and asks.

Together, they answer two questions at once

The voice says who is talking. The face says which camera shows them. Your correction always wins.

Speaking time labelled right

In our tests

We measured how much speaking time Eddie labelled with the right speaker, on the earlier version and on the current version. The current version adds a second model that watches lip movement against the audio.

Two-camera interview

99.0%

Eddie now99.0%
Eddie before93.3%

Three-camera podcast

99.8%

Eddie now99.8%
Eddie before83.1%

These are two internal tests. They are not a published benchmark, and results change with the footage.

How it works

How it works in a project

  1. An interview transcribed on import, each line labelled A, B or C
    01

    Import

    You add your footage. Eddie transcribes every source and separates the voices.

  2. Three cameras synced, with the speaker's own camera selected
    02

    Match

    On a multicam shoot, Eddie matches each voice to the camera that shows that person.

  3. Renaming a speaker in the transcript
    03

    Check

    You see the names. Rename a speaker or fix a line, and your change always stays.

  4. A program track cut to the speaker, captions following the speaker
    04

    Edit

    Eddie cuts, captions and frames with the speaker in mind, then exports.

NLE exports that keep the multicam

Angles travel with the cut.

Premiere Pro and DaVinci Resolve projects carry real multicam clips you can switch. FCPXML carries the same cuts as flat clips.

Every export Eddie produces
Speakers labelled in Premiere Pro, names carried into the editor

Questions

How does Eddie identify who is speaking?

Eddie uses two signals. It separates the voices in the audio and labels each line by speaker. On a multicam shoot, it also watches the mouths on each camera while each speaker talks, and it matches each voice to the camera that shows that person.

Why use faces as well as voices?

Voice labels say who is talking, but not which camera shows them. Faces answer that. In our tests on a two-camera interview, the current version of Eddie labelled 99.0% of speaking time with the right speaker, against 93.3% for the earlier version. On a three-camera podcast it was 99.8% against 83.1%.

Does it work on one camera?

Yes, for voices. Eddie separates the speakers and labels every line. The camera matching applies to multicam shoots, where Eddie needs to know which camera shows which person.

What if Eddie gets a label wrong?

Rename the speaker, move the lines to the right person, or merge two labels. Renaming and merging speakers is free. Eddie never overwrites a label you set by hand, so your correction stays through later automatic passes.

What about a wide shot that shows two people?

When both people are clearly in frame, Eddie labels the camera with both names, from left to right. If it cannot tell, it leaves the camera unlabelled and asks you. Your cuts still follow each speaker's voice, and for a vertical clip Eddie crops each segment onto whoever is speaking.

Does speaker identification change my exports?

It changes the cut. Where you export a multicam edit to the Premiere Pro project or the DaVinci Resolve project, the multicam clips and the angle Eddie chose for each cut come with it. FCPXML carries the same cuts as flat clips.

Try it on your own footage

Start with one prompt. Your first 500 credits are free.