voice-interaction

Name: voice-interaction
Author: Owl-Listener

82stars25forks

How to install voice-interaction?

owl-listener/inclusive-design-skills/voice-interaction

$npx -y skills add Owl-Listener/inclusive-design-skills --skill voice-interaction

Installs into the current project.

Summary

Design voice interactions and speech interfaces that work for people with diverse speech patterns, accents, and communication styles. Use when designing voice commands, voice search, dictation, voice assistants, or any interface that accepts speech input. Triggers on: voice, spee

Files · 1

View on GitHub

SKILL.md

1	# Voice Interaction Design
2
3	Design voice interfaces that work for the full range of human speech —
4	including accents, speech disabilities, non-native speakers, and people
5	in noisy or quiet environments.
6
7	## Who This Is For
8
9	- People with motor disabilities who use voice as primary input
10	- People who stutter, have dysarthria, or other speech differences
11	- Non-native speakers with varied accents
12	- People in environments where typing is impractical
13	- Anyone who prefers voice to typing for certain tasks
14
15	## Core Principles
16
17	### Voice Should Never Be the Only Option
18	- Every voice interaction must have a text/touch/keyboard alternative
19	- Voice is an accelerator, not a gatekeeper
20	- Don't require voice for identity verification or critical actions
21	unless an alternative exists
22
23	### Design for Speech Variation
24	- Support varied pacing — don't cut off slow speakers
25	- Allow generous silence before timing out
26	- Don't penalise repetition, filler words, or self-correction
27	- Support multiple phrasings for the same intent
28	("go back", "previous page", "take me back", "undo")
29
30	### Feedback Must Be Clear
31	- Confirm what the system heard (visual transcript)
32	- Make it easy to correct misrecognition
33	- Show when the system is listening vs. processing vs. waiting
34	- Never execute a destructive action on voice alone without
35	confirmation
36
37	## Design Patterns
38
39	### Flexible Recognition
40	- Accept multiple ways to say the same command
41	- Don't require exact phrasing — intent matters more than syntax
42	- Support "did you mean?" clarification for ambiguous input
43	- Allow users to spell out words the system doesn't recognise
44
45	### Graceful Failure
46	- When recognition fails: show what was heard and offer correction
47	- Never respond with just "I didn't understand" — offer alternatives
48	- Provide a "type instead" option at every failure point
49	- After repeated failures: proactively suggest switching to text input
50
51	### Privacy and Control
52	- Clear visual/audio indicator when microphone is active
53	- Easy one-action mute/stop listening
54	- Don't record or transmit audio without explicit consent
55	- Allow users to review and delete voice data
56
57	## Assessment Questions
58
59	1. Can every voice-activated feature also be completed without voice?
60	2. Does the system handle varied speech patterns without frustration?
61	3. Is there clear feedback showing what the system heard?
62	4. Can users easily correct misrecognition?
63	5. Is it obvious when the system is listening?

People who liked this also viewed

6 picks

Type

voice-interaction

82stars25forks

View on GitHub

How to install voice-interaction?

owl-listener/inclusive-design-skills/voice-interaction

$npx -y skills add Owl-Listener/inclusive-design-skills --skill voice-interaction

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Voice Interaction Design
2
3	Design voice interfaces that work for the full range of human speech —
4	including accents, speech disabilities, non-native speakers, and people
5	in noisy or quiet environments.
6
7	## Who This Is For
8
9	- People with motor disabilities who use voice as primary input
10	- People who stutter, have dysarthria, or other speech differences
11	- Non-native speakers with varied accents
12	- People in environments where typing is impractical
13	- Anyone who prefers voice to typing for certain tasks
14
15	## Core Principles
16
17	### Voice Should Never Be the Only Option
18	- Every voice interaction must have a text/touch/keyboard alternative
19	- Voice is an accelerator, not a gatekeeper
20	- Don't require voice for identity verification or critical actions
21	unless an alternative exists
22
23	### Design for Speech Variation
24	- Support varied pacing — don't cut off slow speakers
25	- Allow generous silence before timing out
26	- Don't penalise repetition, filler words, or self-correction
27	- Support multiple phrasings for the same intent
28	("go back", "previous page", "take me back", "undo")
29
30	### Feedback Must Be Clear
31	- Confirm what the system heard (visual transcript)
32	- Make it easy to correct misrecognition
33	- Show when the system is listening vs. processing vs. waiting
34	- Never execute a destructive action on voice alone without
35	confirmation
36
37	## Design Patterns
38
39	### Flexible Recognition
40	- Accept multiple ways to say the same command
41	- Don't require exact phrasing — intent matters more than syntax
42	- Support "did you mean?" clarification for ambiguous input
43	- Allow users to spell out words the system doesn't recognise
44
45	### Graceful Failure
46	- When recognition fails: show what was heard and offer correction
47	- Never respond with just "I didn't understand" — offer alternatives
48	- Provide a "type instead" option at every failure point
49	- After repeated failures: proactively suggest switching to text input
50
51	### Privacy and Control
52	- Clear visual/audio indicator when microphone is active
53	- Easy one-action mute/stop listening
54	- Don't record or transmit audio without explicit consent
55	- Allow users to review and delete voice data
56
57	## Assessment Questions
58
59	1. Can every voice-activated feature also be completed without voice?
60	2. Does the system handle varied speech patterns without frustration?
61	3. Is there clear feedback showing what the system heard?
62	4. Can users easily correct misrecognition?
63	5. Is it obvious when the system is listening?

People who liked this also viewed

6 picks

Type