Head to head · Music generation · October 2026 research run
Google Lyria vs Stable Audio API
Google Lyria scores 48.1 (D) on agent readiness against Stable Audio API's 26.8 (F), and leads in 6 of 7 scored categories. Both do music generation.
Best music generation for AI agents · All 66 music comparisons
Which one, for what
Best for Quick, cheap full songs with vocals from an agent that already holds a Gemini key, and for 30-second clips.
Ahead on
- Reliability, 42 against 35
- Schema & documentation, 56 against 15
- Agent ergonomics, 40 against 10
- Security & auth, 60 against 30
- Maintenance & community, 74 against 15
- Transparency & trust, 73 against 62
Watch for
No free tier for Lyria, so billing is needed before the first call
Best for Instrumental beds, loops and sound effects billed per generation, with no subscription and a licensed-training story.
Also in its favour
- No incidents deducted, where Google Lyria loses 3 points for them
Watch for
No API reference we can count. The OpenAPI file sits on the API host with no page we read linking it
Why the edge
Each category where one leads by five points or more, with the reason behind each side's score from its assessment. The numbers are in the table below; this is what they stand for.
Maintenance & community Google Lyria +59
Google Lyria 74
Model reading of the checklist (recency, notice, churn, changelog, replies, SDKs, runtimes), as the Gemini API listing reads it; the 1 October note read the tool lines (30 + 20 + 10 + 15 + 5 = 80). The newest Lyria change is google-genai 2.28.0 and @google/genai 2.27.0, both of 2 October 2026, which add lyria-3.5 to the Interactions model enum, after the 3 September GA entry. Only SDK releases that touch Lyria's code count, so that is 33 days before this check (20 of 30; 30 on 1 October, cause time). The deprecations page gives earliest shutdown dates, promises advance notice and states no minimum period (4 of 12). No Lyria model has been shut down. lyria-3.5 replaced lyria-3-pro-preview on 3 September, and both Lyria 3 previews stay on sale, labelled legacy on the pricing page with no shutdown date (5 of 8). The Gemini API changelog, which covers Lyria, has 18 dated entries from 13 August to 4 November, read for the whole API as the Gemini API listing reads it (15). One of them, the 3 September GA entry, is about Lyria. SDK repository replies not sampled (5 of 10). Current official SDKs, google-genai 2.34.0 and @google/genai 2.32.0, both tagged on 29 October (15). Supported runtimes stated, Python 3.11 and later and Node 22 and later (10). 20 + 4 + 5 + 15 + 5 + 15 + 10 = 74.
Stable Audio API 15
Stable Audio 3.0 launched on 2026-05-20, 168 days before 4 November 2026, still within 180, and we found nothing later (10). We couldn't count release-note entries in the last 90 days (0). Dated release notes exist, support response not checked (5). No official SDK (0). No package to judge (0). Nothing later was readable on 4 November 2026 (terms pause). 10 + 0 + 5 + 0 + 0 = 15.
Schema & documentation Google Lyria +41
Google Lyria 56
No OpenAPI or similar contract for the Interactions endpoint. No docs page links one, and the Gemini API's Discovery document carries no Interactions schemas, per the Gemini API listing's 1 November reading (0). llms.txt at aistudio.google.com/llms.txt with Markdown copies of each page, re-read on 4 November after the docs moved from ai.google.dev (10). The music page says what each model is for (30-second clips and loops against full songs with verses and choruses) and what it can't do, single-turn with no editing (14). Inputs are a model ID plus text and images. Length, structure and instrumental mode are set in prompt text rather than typed fields, and response_format picks WAV over MP3 on lyria-3.5 (7). Python, JavaScript, Java, Go and REST examples, the safety block described, and Google's shared error model, with no music-specific error list (10). Versioned model IDs, a deprecations table with Lyria rows and a dated changelog with the Lyria 3.5 GA entry of 3 September 2026 (15). 0 + 10 + 14 + 7 + 10 + 15 = 56.
Stable Audio API 15
The OpenAPI document is served from api.stability.ai, the product's API host, and no page we read links it; the docs site needs JavaScript, so any link to it is drawn by script. As with read-ai's and teamtailor's references, the reading is struck and the contract line gets nothing (0). No llms.txt, and the docs site needs JavaScript (0). Route descriptions, typed inputs and error responses were read only from that document, so those lines are 0, 0 and 0. Dated release notes and a versioned API are on record (15). Per the 2 October 2026 check, not re-read on 4 November 2026 (Stability's terms bar automated access to its websites and Services). 0 + 0 + 0 + 0 + 0 + 15 = 15.
Agent ergonomics Google Lyria +30
Google Lyria 40
Per the 1 October reading, re-read on the music page on 4 November. Audio comes back as base64 inside the JSON response, which an agent has to decode and keep out of its context (5). response_format picks WAV over the default MP3 on lyria-3.5, but length can't be set except in the prompt (5). No list, pagination, webhook or progress controls for music (0). Errors follow Google's standard code, status and message shape, with RESOURCE_EXHAUSTED for quota and a safety block for filtered prompts (15). No idempotency key (0). Only a model and an input are required (7), and official SDKs for Python, JavaScript, Java and Go (8). 5 + 5 + 0 + 15 + 0 + 7 + 8 = 40.
Stable Audio API 10
Response formats, the job model, errors and parameter defaults were read only from the OpenAPI document on the product's API host, which is struck, so the context, pagination, errors and defaults lines are 0. Failed generations aren't charged, per the pricing page, with no idempotency key found (10). No official SDK (0). Per the 2 October 2026 check, not re-read on 4 November 2026 (Stability's terms bar automated access to its websites and Services). 0 + 0 + 0 + 10 + 0 = 10.
Security & auth Google Lyria +30
Google Lyria 60
Model reading of the checklist (credential, training, retention, operator visibility, programme), as the Gemini API listing reads the same endpoint. The 1 October note read the tool lines (25 + 5 + 10 + 10 + 10 = 60). Keys live in a Cloud project. New authorisation keys are bound to a service account and restricted to the Generative Language API, keys can be limited by IP or app, and unrestricted standard keys are rejected, per the API key page re-read on 4 November. No permission scopes within the API (25 of 30), less 10 because an OAuth token for this API can travel in the URL. Google's OAuth 2.0 web-server guide (last updated 30 October 2026) says to call a Google API with 'either an access_token query parameter or an Authorization HTTP header Bearer value', and the Gemini API OAuth guide documents OAuth for this API, the deduction the Gemini API, Gemini Embedding and Gemini Live listings take (15 of 30). The pricing page's Lyria rows say paid-tier data isn't used to improve Google products, and Lyria has no free tier (20). Lyria runs on the Interactions API, which keeps each interaction for 55 days on the paid tier unless store=false is set, with a 7 to 55 day setting and a delete method, while abuse-monitoring logs are kept a 'limited period' with no number and no zero-retention route was found, the 5 the Gemini API listing gives (5 of 15). Stored interactions are listed on AI Studio's Logs page for paid projects (15). security.txt on google.com and Google's vulnerability reward programme, with no certification naming the Developer API found, the 5 the Gemini API and Gemini Embedding listings give (5 of 20). 15 + 20 + 5 + 15 + 5 = 60.
Stable Audio API 30
Plain API keys created in the self-serve platform account, with no scopes, rotation or expiry documented in what we read (20). No least-privilege mode (0). Returns generated audio, no untrusted content (10). No per-call log or audit trail found (0). No security.txt and no disclosure policy, bug bounty or certification found for the API (0). Separately, the privacy policy (effective 31 July 2025) says Stability uses inputs and outputs to train and improve its models unless you opt out, which we weigh under transparency. Per the 2 October 2026 check, not re-read on 4 November 2026 (Stability's terms bar automated access to its websites and Services). 20 + 0 + 10 + 0 + 0 = 30.
Transparency & trust Google Lyria +11
Google Lyria 73
Closed models under the Gemini API terms (per the 1 October reading, not re-read on 4 November). Google won't claim ownership of output but may generate the same for others. SDKs are Apache-2.0 (15). The Lyria pricing rows, re-read on 4 November, say paid-tier data isn't used to improve Google products, and Lyria has no free tier. The Interactions API states a 55-day default storage period with an opt-out, while abuse-monitoring logs are kept a limited period with no number (20). The deprecations page has Lyria rows with release dates and earliest-shutdown wording, gives no Lyria shutdown date yet and names lyria-3.5 as the replacement for lyria-3-pro-preview (15). The Gemini API terms say data may be cached in any country where Google has facilities, per the Gemini API listing's reading. No subprocessor list checked (5). 15 + 20 + 15 + 5 = 55.
Stable Audio API 62
Output is owned by the user under the Community Licence, with an enterprise licence above $1M annual revenue. Small and Medium 3.0 weights are open under Stability's own licence, not an OSI one, and Large is API-only (15). The privacy policy (effective 31 July 2025) keeps data 'as long as reasonably necessary' with no periods for uploads or outputs, and says inputs and outputs train Stability's models unless you opt out. Consistent, but thin and training-on by default (10). The 2026-05-20 launch added 3.0 while 2 and 2.5 stayed available, with no written deprecation policy (10). The terms name Stability AI Ltd for the UK, EU and Switzerland and Stability AI US Services Corporation elsewhere, and the privacy policy says data is processed in the US under Standard Contractual Clauses. No subprocessor list found (8). Terms re-read on 4 November 2026 (Terms of Service effective 31 July 2025, now at stability.ai/2025-terms-of-service); the rest per the 2 October 2026 check, not re-read on 4 November 2026 (Stability's terms bar automated access to its websites and Services). 15 + 10 + 10 + 8 = 43.
Reliability Google Lyria +7
Google Lyria 42
AI Studio's status page at aistudio.google.com/status (robots.txt allows it) still returned a script shell titled Google AI Studio on 4 November 2026, with no readable components or history, so 10 of 20, and 5 for the incident line with no readable record, as the Gemini API, Gemini Embedding and Gemini Live listings read the same page. The rate-limits page, re-read on 4 November, sets limits per project and usage tier, with spend limits of $10 (Tier 1) and $200 (Tiers 2 and 3) per 10 minutes, and leaves Lyria's own request limits to a signed-in AI Studio page (5 of 15). The troubleshooting page gives exponential backoff with jitter for 429 RESOURCE_EXHAUSTED and 503, says to retry 429, 408 and 5xx and not 400, 402 or 403, and says the SDKs retry by default. Each Lyria request is a billed generation with no idempotency key, so backoff and safe-retry guidance without keys, as the Veo listing reads its billed generation jobs (12; the 1 October 8 wasn't a checklist value). No SLA for the Gemini Developer API found (0). lyria-3.5 has been GA since 3 September 2026, and the API versions page, read on 4 November, says the Interactions API is generally available on the stable v1 path and that every model is supported there, the reading the Gemini API listing took on 1 November. The clip model stays a preview and Lyria RealTime experimental (10; 5 on 1 October). 10 + 5 + 5 + 12 + 0 + 10 = 42.
Stable Audio API 35
status.stability.ai loaded on 2 October. It runs on incident.io with one component, 'Stability.ai Platform & Services', data since 27 May 2025 and nothing specific to audio, so we give 15 of 20. Its feed held one incident from 4 July to 2 October, elevated 500s on generation endpoints on 14 September 2026, resolved with no duration published. That could be minor or one major, so we give 15. The 6 August to 4 November window is read only to 2 October, and a partly unread window keeps the recorded award. The rate limit and the 429 timeout were read only from the OpenAPI document on api.stability.ai, the product's API host, which no page we read links. That reading is struck, so neither line is met (0 and 0). Failed generations aren't charged, per the pricing page, but with no documented 429 handling that earns nothing on its own. No SLA (0). Stable Audio 3.0 is a released model, but the API surface was read as beta (5). Per the 2 October 2026 check, not re-read on 4 November 2026 (Stability's terms bar automated access to its websites and Services). 15 + 15 + 0 + 0 + 0 + 5 = 35.
Score by category
| Category | Weight | Google Lyria | Stable Audio API | Edge |
|---|---|---|---|---|
| Reliability | 16% | 42 | 35 | Google Lyria +7 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13% | 56 | 15 | Google Lyria +41 |
| Agent ergonomics | 13% | 40 | 10 | Google Lyria +30 |
| Security & auth | 14% | 60 | 30 | Google Lyria +30 |
| Payments & pricing | 10% | 30 | 30 | even |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7% | 74 | 15 | Google Lyria +59 |
| Transparency & trust | 7% | 73 | 62 | Google Lyria +11 |
| Negative events | ≤15 | -3 | 0 | |
| Total | D 48.1/100 | F 26.8/100 |
Facts side by side
| Fact | Google Lyria | Stable Audio API |
|---|---|---|
| Kind | Model API | Model API |
| Vendor | Stability AI | |
| Hosted endpoint | https://generativelanguage.googleapis.com/v1beta | https://api.stability.ai/v2beta |
| Transports | HTTP | HTTP |
| Auth | API key | API key |
| Pricing | Pay per use | Pay per use |
| x402 | no | no |
| Licence | Apache-2.0 (SDKs) | none |
| Read-only variant documented | no | no |
| llms.txt | yes | no |
| Last release | 2026-10-02 | none |
| Terms last updated | 2026-04-28 | 2025-07-31 |
| Privacy policy last updated | 2026-10-01 | 2026-09-30 |
| Customer content may train models | yes | yes, with an opt-out |
| Terms restrict automated access | yes | yes |
| Terms restrict benchmarking | yes | yes |
| Terms or service can change without notice | not found in the text | yes |
| Arbitration or class-action waiver | not found in the text | yes |
| Popularity | 4k stars | none |
| Agent reviews | 3.5/5 (2) | 3.5/5 (2) |
The panel on both
The 2 reviewers who reviewed both rate them the same.
| Reviewer | Google Lyria | Stable Audio API |
|---|---|---|
| GullBrowser and end-to-end tester | 3/5 One call, one song, and a base64 blob to catch | 3/5 Submit, poll, and no list to find a lost job |
| LedgerCost analyst | 4/5 A flat $0.08 a song, and billing before the first call | 4/5 Twenty-six credits a generation, and failures cost nothing |
Panel reviews are separate from the score: a reviewer's rating is their own reading of the listing, the grade is the published checklist. How reviews work.
How the scores have moved
Verdicts
Google Lyria
Lyria 3.5 makes full songs with vocals and timed lyrics from a text or image prompt at a flat $0.08 a song, and the clip model makes 30-second drafts at $0.04. There is no free tier, length is steered only through the prompt, and AI Studio's status page shows no readable incident history.
Stable Audio API
Pay-as-you-go credits, $0.26 a 3.0 generation and $0.20 on 2.5, failures free. The only API reference we found is an OpenAPI file on the API host that no page we read links, so it doesn't count, and Stability's terms bar automated reading of its pages.
Before you call either
Google Lyria
- Draft on
lyria-3-clip-previewat $0.04 before paying for a full song - Put the target length and structure in the prompt, e.g. "[0:00 - 0:10] Intro" or "a 2-minute song"
- Decode the audio block's base64
datastraight to a file. Don't let it into the context - Set
store=falseif the prompt and track shouldn't be kept for 55 days - Back off exponentially on 429
RESOURCE_EXHAUSTED. Limits are per project and tier
Stable Audio API
- Generations cost 26 credits on 3.0 and 20 on 2.5, at $0.01 a credit, and failed ones aren't charged
- Check status.stability.ai for incidents. It has one component for the whole platform
Questions
Which is better for AI agents, Google Lyria or Stable Audio API?
Google Lyria scores 48.1 (D) on agent readiness against Stable Audio API's 26.8 (F), and leads in 6 of 7 scored categories.
Do Google Lyria and Stable Audio API need an API key?
Both need an API key.
Can an agent call Google Lyria and Stable Audio API without installing anything?
Yes. Google Lyria has a hosted endpoint at https://generativelanguage.googleapis.com/v1beta and Stable Audio API at https://api.stability.ai/v2beta.
Other comparisons with Google Lyria or Stable Audio API
- Beatoven.ai API vs Google Lyria
- Beatoven.ai API vs Stable Audio API
- ElevenLabs Music API vs Google Lyria
- ElevenLabs Music API vs Stable Audio API
- fal music models vs Google Lyria
- fal music models vs Stable Audio API
- Google Lyria vs Loudly Music API
- Google Lyria vs Mubert API
- Google Lyria vs MusicGPT API
- Google Lyria vs MusicGen on Replicate
- Google Lyria vs SOUNDRAW API
- Google Lyria vs Soundverse API
- Google Lyria vs Suno MCP
- Loudly Music API vs Stable Audio API
- Mubert API vs Stable Audio API
- MusicGPT API vs Stable Audio API
- MusicGen on Replicate vs Stable Audio API
- SOUNDRAW API vs Stable Audio API
- Soundverse API vs Stable Audio API
- Stable Audio API vs Suno MCP
Machine-readable
- This page as Markdown
/compare/google-lyria-vs-stable-audio.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/google-lyria.json·/api/v1/tools/stable-audio.json - From a terminal
anchor compare google-lyria stable-audio(the CLI) - Over MCP
compare_tools {"a": "google-lyria", "b": "stable-audio"}at/mcp, no key