Hands-free voice tagging
Tag clips by speaking instead of pressing a button — one phrase can set the tag, zone, players and qualifiers at once.
On this page
Hands-free voice tagging lets you tag a clip by saying it instead of pressing a hotkey or button. A single spoken phrase can fill in everything a tag button, a zone click, a player assignment and a qualifier pick would normally take several steps to do — say "gol nuestro, banda derecha, contragolpe de Juan" and cliply creates one clip tagged Goal, in the right-wing zone, qualified Counter-attack, with Juan assigned — all from one sentence, without taking your eyes off the video.
Hands-free voice tagging is rolling out gradually — contact support to ask about turning it on for your org.
Turning it on
The workspace has three capture modes, and only one is active at a time:
- Auto (default) — press a tag button and it stamps a clip instantly.
- Manual — record-style: press to open a clip, press again to close it.
- Hands-free — tag by voice.
Switch to Hands-free from the mic button in the transport bar (tooltip Hands-free tagging, shortcut ⌥Space). It stays selected across sessions until you switch to Auto or Manual — toggling the same mode off returns you to Auto.
Tagging by voice
Once Hands-free is active, a mic strip appears above the deck showing Press ⌥Space or tap to talk.
To tag a clip:
- Press ⌥Space (or tap the mic button in the strip) to start a take, then press ⌥Space again (or tap the mic button) to stop. You can also press and hold the mic button instead of tapping it — releasing it stops the take, walkie-talkie style.
- Say your tag — a bare tag name, or a fuller phrase with zone, players and qualifiers (see below).
- Stop the take. The strip switches to Listening while recording, then to Resolving… while cliply works out what you said.
Clicking away and losing window focus discards the current take instead of creating a clip.
The clip's timestamp is captured the instant you start speaking, not when recognition finishes — so however long it takes to resolve a phrase, the clip never drifts from the moment the action happened.
One phrase, four dimensions
A single utterance can resolve up to four things at once:
| Dimension | Example |
|---|---|
| Tag | "gol nuestro" → Goal |
| Zone | "banda derecha" → the right-wing zone on your team's zone map |
| Qualifier | "contragolpe" → the Counter-attack variant |
| Player | "de Juan" → Juan assigned to the clip |
cliply resolves what you say against your own organization's catalog — its tags, its zone map, its roster, and its variant qualifiers — not a fixed vocabulary. Matching is semantic, not exact-word, so it tolerates accents, phrasing, and the odd mis-hearing; you don't need to speak a rigid command syntax.
When cliply isn't confident
If the parsed result is a clear, confident match, the clip is created immediately — the same saved-clip pill you'd see after a button press shows up, and ⌘Z (or the pill's own Undo) removes it if you spoke by mistake.
If cliply isn't confident it heard you right, it asks first instead of guessing: a confirmation card appears above the deck showing what it heard and the parsed event as tag · zone · player · qualifier (for example, "Goal · Right wing · Juan · Counter-attack"). Click it to create the clip — or, if the tag isn't quite right, pick one of the alternate tags cliply also offers. Dismiss the card (or ignore it) and nothing is created.
Cost
Voice tagging is priced per spoken phrase, not per word:
- A single, plain tag name (just the tag, nothing else) is recognized locally in Chrome and Edge — it's free and instant, no network round-trip.
- Anything richer — a zone, a player, a qualifier, or a phrase cliply doesn't recognize locally — is resolved with AI, at a flat ~5 credits per phrase.
- Nothing is charged if cliply doesn't catch any speech, or if resolving the phrase fails.
Hands-free voice tagging needs a paid plan or available AI credits. If your org doesn't have either, the mic button shows locked with an upgrade prompt. See How credits work for balances and top-ups.
Browser and desktop support
Hands-free tagging works best in Chrome or Edge, where the free local fast-path for plain tag names is available. Recording and the full AI-resolved path work in any modern browser with microphone access.
It's web-only for now — the desktop app doesn't support hands-free tagging yet. Use Auto or Manual capture there instead.
Good to know
- No ambient listening. cliply only records between starting and stopping a take (⌥Space or the mic button) — there's no always-on or ambient listening.
- Tags and events. Speaking a tag creates a clip; speaking a match event (like "corner" or "kickoff") stamps that event on the timeline. It doesn't control playback or take other actions by voice.
- No wake word. You start and stop each phrase yourself — there's nothing to say to "activate" listening.