Lyria 3 Clip Preview is Google’s music-generation profile for short clips, loops and previews. It accepts a text prompt or image inspiration and returns text and audio. The published profile describes 30-second clips with 48 kHz stereo audio, including vocals, timed lyrics and full instrumental arrangements.
Name the purpose of the clip and the mood it should carry. A short opening theme can specify a restrained introduction and a clear arrival; a background cue can identify the pace and texture needed beneath a visual scene. State whether the result should feature vocals or be instrumental, and name the musical elements that matter to the brief.
Keep the structure small enough for the clip. Identify the opening, the main phrase and the ending or loop point. If words matter, provide the intended lyrical idea or wording and inspect the actual sung result. The musical brief should distinguish the vocal content from directions about the arrangement.
When supplying an image, explain which scene or mood it contributes to the music request. A calm landscape and a crowded night scene suggest different directions, but the desired emotional role should still be explicit in the text. Keep the image with the prompt when comparing the returned clip with the intended concept.
Review the balance between vocals, instruments and the main musical phrase. For a loop, listen through the end and beginning together; for a preview, check whether the short duration communicates the intended direction. A clip that accompanies an edit should be reviewed against that edit rather than only in isolation.
Save the actual audio and any accompanying text with the brief. Inspect its file properties when preparing playback or importing it into an editor, and preserve any lyric or timing information returned by the request. The music is the model’s output; cuts, titles, visual transitions and a final production mix can be arranged around that inspected asset.
This exact Clip Preview profile is suited to a compact musical deliverable. Keep its short-form role distinct when planning a longer composition, and choose the returned clip by listening to the complete phrase, vocal wording and ending.
", "aboutText": "Lyria 3 Clip Preview is Google’s music-generation profile for short clips, loops and previews. It accepts a text prompt or image inspiration and returns text and audio. The published profile describes 30-second clips with 48 kHz stereo audio, including vocals, timed lyrics and full instrumental arrangements.\n\n### Describe the musical moment\n\nName the purpose of the clip and the mood it should carry. A short opening theme can specify a restrained introduction and a clear arrival; a background cue can identify the pace and texture needed beneath a visual scene. State whether the result should feature vocals or be instrumental, and name the musical elements that matter to the brief.\n\nKeep the structure small enough for the clip. Identify the opening, the main phrase and the ending or loop point. If words matter, provide the intended lyrical idea or wording and inspect the actual sung result. The musical brief should distinguish the vocal content from directions about the arrangement.\n\n### Image inspiration and arrangement\n\nWhen supplying an image, explain which scene or mood it contributes to the music request. A calm landscape and a crowded night scene suggest different directions, but the desired emotional role should still be explicit in the text. Keep the image with the prompt when comparing the returned clip with the intended concept.\n\nReview the balance between vocals, instruments and the main musical phrase. For a loop, listen through the end and beginning together; for a preview, check whether the short duration communicates the intended direction. A clip that accompanies an edit should be reviewed against that edit rather than only in isolation.\n\n### Retain the listening artifact\n\nSave the actual audio and any accompanying text with the brief. Inspect its file properties when preparing playback or importing it into an editor, and preserve any lyric or timing information returned by the request. The music is the model’s output; cuts, titles, visual transitions and a final production mix can be arranged around that inspected asset.\n\nThis exact Clip Preview profile is suited to a compact musical deliverable. Keep its short-form role distinct when planning a longer composition, and choose the returned clip by listening to the complete phrase, vocal wording and ending.", "editorialOverlay": { "copy_fields": null, "copy_sha256": null, "copy_source": null, "html_sha256": "bf5614a9039bd7bbb1c1cbd5664fa35e2f28d41a4bb7219d69d5675ff76bd1ba", "module_sha256": "ee9dc1c50b1e6a8fb7fa062030fcb4646b9aaaeb08be513b723a5a92a7290f06", "raw_model_unchanged": true, "schema": "ailoot-native-model-editorial-v1" }, "locale": "en", "methods": [ { "html": "google/lyria-3-clip-previewLyria 3 Clip Preview is Google’s music model for short clips, loops and previews. It takes text or image inspiration and produces 30-second music with 48 kHz stereo audio, supporting vocals, timed lyrics and instrumental arrangements.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Lyria 3 Clip Preview is Google’s music-generation profile for short clips, loops and previews. It accepts a text prompt or image inspiration and returns text and audio. The published profile describes 30-second clips with 48 kHz stereo audio, including vocals, timed lyrics and full instrumental arrangements.
Name the purpose of the clip and the mood it should carry. A short opening theme can specify a restrained introduction and a clear arrival; a background cue can identify the pace and texture needed beneath a visual scene. State whether the result should feature vocals or be instrumental, and name the musical elements that matter to the brief.
Keep the structure small enough for the clip. Identify the opening, the main phrase and the ending or loop point. If words matter, provide the intended lyrical idea or wording and inspect the actual sung result. The musical brief should distinguish the vocal content from directions about the arrangement.
When supplying an image, explain which scene or mood it contributes to the music request. A calm landscape and a crowded night scene suggest different directions, but the desired emotional role should still be explicit in the text. Keep the image with the prompt when comparing the returned clip with the intended concept.
Review the balance between vocals, instruments and the main musical phrase. For a loop, listen through the end and beginning together; for a preview, check whether the short duration communicates the intended direction. A clip that accompanies an edit should be reviewed against that edit rather than only in isolation.
Save the actual audio and any accompanying text with the brief. Inspect its file properties when preparing playback or importing it into an editor, and preserve any lyric or timing information returned by the request. The music is the model’s output; cuts, titles, visual transitions and a final production mix can be arranged around that inspected asset.
This exact Clip Preview profile is suited to a compact musical deliverable. Keep its short-form role distinct when planning a longer composition, and choose the returned clip by listening to the complete phrase, vocal wording and ending.
POST /v1/music/generationstextmusic| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits google/lyria-3-clip-preview | Default— |
Fieldprompt | Typestring | RequirementRequired | Values & limits Minimum length: 1 | Default— |
text_to_music · Required: prompt
| Parameter | Contract |
|---|---|
Parametermaterial_types | Contracttext |
Parameterrequired | Contractnull |
Parameteroptional_controls | Contractnull |
Lifecycle: synchronous_result_then_owned_library
GET /v1/media/tasks/{task_id} · actual returned task_id or media library record
GET /v1/media/assets/{asset_id}/content
GET /v1/media/assets
GET /v1/media/assets/{asset_id}
Method shapes and IDs are exact; supplier capability is separate from admission.
POST /v1/music/generationsDelivered clips × base clip rate. The per-request reference is not added. Examples are before applicable adjustments.
1 × $0.04 = $0.04
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
Model-level reference schedules do not change method selection, quotes or charges. Active charges use the selected Ailoot method rates.
| Configuration | Service tier | Context condition | Charge |
|---|---|---|---|
| ConfigurationUltra | Service tierstandard | Context condition{} | Charge Output · music $0.08 per song |
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_PROMPT_FILE:?Set your actual UTF-8 music brief}"\nexport AILOOT_PROMPT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "google/lyria-3-clip-preview", "prompt": ""}')\nf=Path(os.environ["AILOOT_PROMPT_FILE"])\nif not f.is_file():raise SystemExit("Choose your actual UTF-8 brief")\np['prompt']=f.read_text(encoding="utf-8")\nif not p['prompt'].strip():raise SystemExit("Brief must contain text")\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/music/generations \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\nexport AILOOT_API_KEY\npython3 - <<'PY_RESULT'\nimport json, os, subprocess\nfrom pathlib import Path\nfrom urllib.parse import urljoin, urlparse\nresult=json.loads(Path("result.json").read_text(encoding="utf-8"))\nprint(json.dumps(result,ensure_ascii=False,indent=2))\nfor number,clip in enumerate(result.get("data") or []):\n u=urlparse(urljoin("https://api.ailoot.ai",clip["url"]))\n if u.scheme!="https" or not u.hostname or u.username or u.password:\n raise SystemExit("Result URL must be HTTPS without embedded credentials")\n owned=u.netloc=="api.ailoot.ai" and u.path.startswith("/v1/media/assets/") and u.path.endswith("/content")\n args=["curl","--fail-with-body","--silent","--show-error",u.geturl()]\n if owned: args += ["-H","Authorization: Bearer "+os.environ["AILOOT_API_KEY"]]\n raw=subprocess.check_output(args)\n ext="wav" if raw.startswith(b"RIFF") and raw[8:12]==b"WAVE" else "flac" if raw.startswith(b"fLaC") else "ogg" if raw.startswith(b"OggS") else "mp3" if raw.startswith(b"ID3") or raw[:1]==b"\\xff" else "bin"\n f=Path("music-"+str(number)+"."+ext);f.write_bytes(raw)\n print("Saved",f,clip.get("asset_id"))\n\nPY_RESULT\ncomplete owned audio clips / JSON links
GET /v1/media/tasks/{task_id}GET /v1/media/assets/{asset_id}/contentGET /v1/media/assetsGET /v1/media/assets/{asset_id}Keep every complete returned response, file and content part.
Save/fetch every returned clip and preserve actual ID, MIME and metadata. The method is synchronous; no separate Ailoot music generationpollingURL is introduced.
If a music result requires a check, keep the original operation_id/X-Client-Request-ID and returned clip information. Recover existing owned clips through the media library using actual task_id or asset_id values. Do not resubmit the music request or construct a generation polling URL from operation_id.
| Field | Type |
|---|---|
Fieldmodel | Typestring |
Fieldresponse_id | Typestring |
Fielddata[] | Typeowned clip record |
| Response | Condition | Next step |
|---|---|---|
Response400 · invalid_request_error | ConditionInvalid required fields, material representation or parameter value | Next stepCorrect the indicated fields before a new creation request. |
Responseserver_error | ConditionThe returned response says the operation or result requires a check | Next stepKeep the original returned operation/task ID, request headers and response; continue supported reads of that original operation. Do not resubmit the creation request. |
Ailoot google/lyria-3-clip-preview
Use the method paths shown above.