lyria

Name: lyria
Author: calesthio

21installs4.9kforks

How to install lyria?

calesthio/openmontage/lyria

$npx -y skills add calesthio/OpenMontage --skill lyria

Installs into the current project.

Summary

Generate and validate music with Google Lyria 3 through the Gemini Interactions API. Use before calling OpenMontage google_music, designing Lyria 3 Clip or Pro prompts, using image-to-music or custom lyrics, choosing between Lyria 3 and Lyria RealTime, diagnosing Google music-g

Files · 1

View on GitHub

SKILL.md

1	# Google Lyria 3
2
3	Use Lyria 3 as a single-turn music generator. Keep it distinct from Lyria RealTime, which is an experimental WebSocket model for continuously steered instrumental performance.
4
5	Read [references/api-and-prompting.md](references/api-and-prompting.md) when choosing a model, designing vocals or custom lyrics, using image inputs, debugging the response, or checking current limits and pricing.
6
7	## Required Workflow
8
9	1. Confirm the intended role: underscore, loop, instrumental cue, or full song.
10	2. Confirm vocals, language, target duration, musical structure, and delivery format.
11	3. Announce the provider, exact model, estimated per-request cost, and whether the call is exploratory or final.
12	4. Write one structured prompt using the contract below.
13	5. Make one approved generation call. Treat a retry as another potentially billable stochastic generation.
14	6. Preserve the returned provider source unchanged.
15	7. Probe the actual file and listen before recording duration, format, or approval metadata.
16	8. Derive a separate production master when the edit requires an exact duration.
17
18	## Choose The Model Deliberately
19
20	\| Need \| Model \| Contract \|
21	\|---\|---\|---\|
22	\| Prompt iteration, preview, loop, exact 30-second source \| `lyria-3-clip-preview` \| Always generates a 30-second MP3; currently $0.04/request \|
23	\| Full song, vocals, longer structure, image-conditioned score \| `lyria-3-pro-preview` \| Prompt-influenced duration up to roughly three minutes; currently $0.08/request \|
24	\| Live, continuously steered instrumental performance \| `lyria-realtime-exp` \| Separate WebSocket workflow; do not route through `google_music` \|
25
26	The current OpenMontage `google_music` adapter is locked to `lyria-3-pro-preview`. It does not expose Clip, WAV response selection, multiple images, or RealTime controls. Surface that limitation rather than implying those options are available through the adapter.
27
28	Do not change models silently. For a 30-second video, either obtain approval for Pro plus exact-duration mastering or use Clip through an explicitly supported path.
29
30	## Build The Prompt
31
32	Specify, in this order:
33
34	1. Purpose and duration — what the music supports and the requested length.
35	2. Genre and era — use musical vocabulary, not a living artist imitation.
36	3. Tempo and harmony — BPM or tempo range, meter, key or tonal center.
37	4. Instrumentation and texture — name lead, rhythm, bass, and ambient layers.
38	5. Structure — timestamped sections or `[Intro]`, `[Verse]`, `[Chorus]`, `[Bridge]`, `[Outro]`.
39	6. Dynamics and synchronization — entrances, rests, builds, hits, and holds tied to edit times.
40	7. Vocal policy — instrumental-only constraints, a vocal profile, or clearly separated custom lyrics.
41	8. Mix and ending — density, foreground/background role, headroom character, and final decay.
42	9. Exclusions — unwanted vocals, instruments, gestures, clichés, abrupt endings, or copyrighted material.
43
44	For video underscore, use timestamp windows that cover the full requested duration. Ask for one primary change per window and identify the exact synchronization moment.
45
46	For instrumental-only output, say all of the following when they matter:
47
48	```text
49	Instrumental only. No lead or backing vocals, speech, choir, humming,
50	vocal chops, spoken samples, lyrical fragments, or recognizable quotations.
51	```
52
53	For custom lyrics, put performance direction before a separate `Lyrics:` block and use section labels. Prompt in the language the singer should use.
54
55	## Direct Vocals Deliberately
56
57	When vocals are requested, define these before writing the prompt:
58
59	1. Vocal role — solo lead, duet, call-and-response, backing ensemble, or vocal texture.
60	2. Language and script — name the sung language and keep the custom lyrics in one intentional script; do not silently transliterate or code-switch.
61	3. Singer profile — voice type or range, timbre, intensity, diction, ornamentation, and emotional distance. Do not imitate a named artist.
62	4. Section behavior — state where the lead enters, where harmonies or echoes appear, and which sections remain instrumental.
63	5. Lyric contract — separate directions from a `Lyrics:` block, use `[Verse]`, `[Chorus]`, `[Bridge]`, and `[Outro]`, and reserve parentheses for intentional backing-vocal echoes.
64
65	Treat the returned vocal as untrusted until auditioned. Check lyric adherence, language drift, pronunciation, intelligibility, unwanted backing vocals, vocal/instrument balance, and whether the performance follows the requested emotional arc. A technically valid file with poor diction or altered lyrics is not an app

People who liked this also viewed

6 picks

Type

lyria

21installs4.9kforks

View on GitHub

How to install lyria?

calesthio/openmontage/lyria

$npx -y skills add calesthio/OpenMontage --skill lyria

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Google Lyria 3
2
3	Use Lyria 3 as a single-turn music generator. Keep it distinct from Lyria RealTime, which is an experimental WebSocket model for continuously steered instrumental performance.
4
5	Read [references/api-and-prompting.md](references/api-and-prompting.md) when choosing a model, designing vocals or custom lyrics, using image inputs, debugging the response, or checking current limits and pricing.
6
7	## Required Workflow
8
9	1. Confirm the intended role: underscore, loop, instrumental cue, or full song.
10	2. Confirm vocals, language, target duration, musical structure, and delivery format.
11	3. Announce the provider, exact model, estimated per-request cost, and whether the call is exploratory or final.
12	4. Write one structured prompt using the contract below.
13	5. Make one approved generation call. Treat a retry as another potentially billable stochastic generation.
14	6. Preserve the returned provider source unchanged.
15	7. Probe the actual file and listen before recording duration, format, or approval metadata.
16	8. Derive a separate production master when the edit requires an exact duration.
17
18	## Choose The Model Deliberately
19
20	\| Need \| Model \| Contract \|
21	\|---\|---\|---\|
22	\| Prompt iteration, preview, loop, exact 30-second source \| `lyria-3-clip-preview` \| Always generates a 30-second MP3; currently $0.04/request \|
23	\| Full song, vocals, longer structure, image-conditioned score \| `lyria-3-pro-preview` \| Prompt-influenced duration up to roughly three minutes; currently $0.08/request \|
24	\| Live, continuously steered instrumental performance \| `lyria-realtime-exp` \| Separate WebSocket workflow; do not route through `google_music` \|
25
26	The current OpenMontage `google_music` adapter is locked to `lyria-3-pro-preview`. It does not expose Clip, WAV response selection, multiple images, or RealTime controls. Surface that limitation rather than implying those options are available through the adapter.
27
28	Do not change models silently. For a 30-second video, either obtain approval for Pro plus exact-duration mastering or use Clip through an explicitly supported path.
29
30	## Build The Prompt
31
32	Specify, in this order:
33
34	1. Purpose and duration — what the music supports and the requested length.
35	2. Genre and era — use musical vocabulary, not a living artist imitation.
36	3. Tempo and harmony — BPM or tempo range, meter, key or tonal center.
37	4. Instrumentation and texture — name lead, rhythm, bass, and ambient layers.
38	5. Structure — timestamped sections or `[Intro]`, `[Verse]`, `[Chorus]`, `[Bridge]`, `[Outro]`.
39	6. Dynamics and synchronization — entrances, rests, builds, hits, and holds tied to edit times.
40	7. Vocal policy — instrumental-only constraints, a vocal profile, or clearly separated custom lyrics.
41	8. Mix and ending — density, foreground/background role, headroom character, and final decay.
42	9. Exclusions — unwanted vocals, instruments, gestures, clichés, abrupt endings, or copyrighted material.
43
44	For video underscore, use timestamp windows that cover the full requested duration. Ask for one primary change per window and identify the exact synchronization moment.
45
46	For instrumental-only output, say all of the following when they matter:
47
48	```text
49	Instrumental only. No lead or backing vocals, speech, choir, humming,
50	vocal chops, spoken samples, lyrical fragments, or recognizable quotations.
51	```
52
53	For custom lyrics, put performance direction before a separate `Lyrics:` block and use section labels. Prompt in the language the singer should use.
54
55	## Direct Vocals Deliberately
56
57	When vocals are requested, define these before writing the prompt:
58
59	1. Vocal role — solo lead, duet, call-and-response, backing ensemble, or vocal texture.
60	2. Language and script — name the sung language and keep the custom lyrics in one intentional script; do not silently transliterate or code-switch.
61	3. Singer profile — voice type or range, timbre, intensity, diction, ornamentation, and emotional distance. Do not imitate a named artist.
62	4. Section behavior — state where the lead enters, where harmonies or echoes appear, and which sections remain instrumental.
63	5. Lyric contract — separate directions from a `Lyrics:` block, use `[Verse]`, `[Chorus]`, `[Bridge]`, and `[Outro]`, and reserve parentheses for intentional backing-vocal echoes.
64
65	Treat the returned vocal as untrusted until auditioned. Check lyric adherence, language drift, pronunciation, intelligibility, unwanted backing vocals, vocal/instrument balance, and whether the performance follows the requested emotional arc. A technically valid file with poor diction or altered lyrics is not an app

People who liked this also viewed

6 picks

Type