Lyria 3.5 vs Stable Audio 3 Medium

Why this pair: Hosted and open-weight music generation models from Google DeepMind and Stability AI

Benchmark Performance

Available Benchmarks

No Protocol-Matched Benchmark Yet.Results appear here only when both models share the same benchmark version, metric, evaluation protocol, and evidence class.
FieldAt a Glance
Google DeepMind · activeLyria 3.5Verified Sep 3, 2026
Stability AI · activeStable Audio 3 MediumVerified Aug 28, 2026

Technical Differences

Side-by-Side Facts

CuratedIndexable
FieldLyria 3.5stable-audio-3-medium
DeveloperGoogle DeepMindStability AI
FamilyLyriaStable Audio 3 Medium
ModelLyria 3.5stable-audio-3-medium
VersionLyria 3.5stable-audio-3-medium
Lifecycleactiveactive
Released2026-07-292026-05-20
Knowledge cutoffUnknownUnknown
Input modalitiesText, ImageText
Output modalitiesText, AudioAudio
Context window1,049KUnknown
Total parametersUnknown2.3B
Active parametersUnknownUnknown
LicenseUnknownother
Open weightsNoYes
API availableYesYes
Self-hostableNoYes
Provider accessGoogle AI (Standard), Google Gemini (Standard)Hugging Face (Standard)
Capabilitiesgeneration, image-to-music, lyrics, music-generation, synthid, vocalsgeneration

13 comparable fields · 11 material differences · Editorially curated pair passes the primary-source comparison gate

Lyria 3.5 Capabilities

generationimage-to-musiclyricsmusic-generationsynthidvocals
Input price
Output price
Serving providers2
Canonical IDlyria-3.5

Stable Audio 3 Medium Capabilities

generation
Input price
Output price
Serving providers1
Canonical IDstabilityai/stable-audio-3-medium

Internal Comparison Graph

Related Comparisons

All audio comparisons →
APairBContext
vsdeveloper peerstext

Primary Evidence

Sources and Freshness

Questions

Lyria 3.5 vs Stable Audio 3 Medium FAQs

Is Lyria 3.5 or Stable Audio 3 Medium better for coding?+

This comparison does not currently contain a protocol-matched coding benchmark for both Lyria 3.5 and Stable Audio 3 Medium, so Model Markets cannot name a coding leader from pricing, context size, or capability labels alone.

Which is cheaper, Lyria 3.5 or Stable Audio 3 Medium?+

Neither model has a directly sourced input price in this comparison. Neither model has a directly sourced output price in this comparison.

Which has a larger context window, Lyria 3.5 or Stable Audio 3 Medium?+

Neither model has a larger sourced context window in this comparison. Lyria 3.5 is 1,049K and Stable Audio 3 Medium is —.

Which performs better in benchmarks, Lyria 3.5 or Stable Audio 3 Medium?+

There is no overall benchmark winner: At least two independently verified, protocol-matched benchmarks are required for an overall winner.

Can Lyria 3.5 or Stable Audio 3 Medium be self-hosted?+

Stable Audio 3 Medium is the only model in this pair currently marked as self-hostable. Lyria 3.5 is not marked open weight; Stable Audio 3 Medium is open weight.

Can Lyria 3.5 and Stable Audio 3 Medium understand images?+

Lyria 3.5 is documented with image input; Stable Audio 3 Medium is not documented with image input. This reflects supported input modalities, not vision quality.

Which can generate longer answers, Lyria 3.5 or Stable Audio 3 Medium?+

Neither has a larger sourced maximum output. Lyria 3.5 is 66K and Stable Audio 3 Medium is —.

Do Lyria 3.5 and Stable Audio 3 Medium support reasoning and tool use?+

Lyria 3.5: image input. Stable Audio 3 Medium: none of these features are definitively sourced. Feature support does not establish relative quality.

Which is available from more inference providers, Lyria 3.5 or Stable Audio 3 Medium?+

Lyria 3.5 has 2 sourced provider routes; Stable Audio 3 Medium has 1, so Lyria 3.5 has broader tracked availability.

Which offers better value, Lyria 3.5 or Stable Audio 3 Medium?+

There is no universal value winner. Compare the input and output prices above with the matched benchmark result for your workload: cheaper tokens can be offset by different quality, token usage, latency, or provider availability.

Send Feedback