Search by voice
Understand who made a statement as well as what was said.
Video intelligence
Separate the voices.
Keep the conversation clear.
Anjin assigns speech to distinct speakers, lets your team name them and carries that identity through transcript search and editorial planning.
One video or an entire archive.
Speaker diarisation product demonstration
Speakers
SpeakersDIARISATION COMPLETE
J46%
Jocko
SPEAKER 1
M31%
Matt
SPEAKER 2
J23%
Jeff
SPEAKER 3
27:44Jockoand it just locked in
What is speaker diarisation for video?
The separation of recorded speech into consistent speaker-labelled segments.
Speaker labels are stored at transcript level and group speakers can be named through the API. Naming is snapshotted into planning work to keep results stable.
Controls and evidence
See what the system used and produced.
Useful automation leaves something a person can inspect. Anjin keeps the edit connected to its brief, source media and output settings.
SPEAKER DIARISATIONVERIFIABLE OUTPUT
- diar_label
- The stable detected label for a voice in a source group.
- speaker_name
- A human-readable name supplied by your team.
- transcript
- Timed words associated with the detected speaker.
- snapshot
- Names captured for consistent asynchronous planning.
Why it matters
More control, less timeline work.
Clarify cut plans
Review multi-speaker edits without anonymous transcript blocks.
Improve captions
Carry clearer speaker context into downstream editorial outputs.
Fit and boundaries
Use the capability where it genuinely helps.
Anjin is strongest on speech-led recorded material where the editorial job can be described clearly and every selected moment needs to remain verifiable. It supports human judgement with searchable evidence, a reviewable plan and structured outputs.
A strong fit
Recorded knowledge with a story inside it
Interviews, podcasts, webinars, discussions and archive programmes benefit when the useful material is distributed across a long recording or several selected sessions.
Keep elsewhere
Final craft and image-led montage
Detailed colour, sound design, motion graphics and wordless visual storytelling remain finishing tasks for a professional editor and their preferred creative tools.
Evaluation checklist
What should you verify before adopting speaker diarisation?
diar_label
Confirm that the workflow exposes this clearly: the stable detected label for a voice in a source group.
speaker_name
Confirm that the workflow exposes this clearly: a human-readable name supplied by your team.
transcript
Confirm that the workflow exposes this clearly: timed words associated with the detected speaker.
snapshot
Confirm that the workflow exposes this clearly: names captured for consistent asynchronous planning.
Put it into practice
Start with a complete editing brief.
Panel discussion argumentCompose a coherent argument across several speakers while preserving attribution.Open the brief →Customer interview evidence reelTurn selected interviews into a concise, traceable evidence composition.Open the brief →Multicamera podcast editPlan the narrative and motivated camera changes before rendering.Open the brief →
Questions about speaker diarisation
- What does speaker diarisation do?
- It answers who spoke when by assigning speech segments to consistent speaker labels within the recording.
- Is diarisation the same as voice identification?
- No. Diarisation separates voices. A person or system still needs to attach a real name to a detected speaker label.
- Can speakers be renamed?
- Yes. Anjin provides speaker naming controls so plans can use recognisable names instead of generic labels.
- Does it work with several camera angles?
- Yes. Speaker information belongs to the synchronised source group and can inform planning across its available angles.
Use speaker diarisation in your next edit.
Start with footage you already have and a clear description of the result you need.
One video or an entire archive.