Lyria 3.5 vs VibeVoice ASR Streaming 7B

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 4, 2026
Microsoft · activeVibeVoice ASR Streaming 7BVerified Sep 2, 2026

Technical Differences

Side-by-Side Facts

Indexable
FieldLyria 3.5VibeVoice-ASR-Streaming-7B
DeveloperGoogle DeepMindMicrosoft
FamilyLyriaVibevoice ASR Streaming
ModelLyria 3.5VibeVoice-ASR-Streaming-7B
VersionLyria 3.5VibeVoice-ASR-Streaming-7B
Lifecycleactiveactive
Released2026-07-292026-09-03
Knowledge cutoffUnknownUnknown
Input modalitiesText, ImageAudio
Output modalitiesText, AudioText
Context window1,049KUnknown
Total parametersUnknown8.7B
Active parametersUnknownUnknown
LicenseUnknownmit
Open weightsNoYes
API availableYesNo
Self-hostableNoYes
Provider accessGoogle AI (Standard), Google Gemini (Standard)Unknown
Capabilitiesgeneration, image-to-music, lyrics, music-generation, synthid, vocalsdiarization, hotwords, multilingual, streaming, transcription
Streaming chunkUnknown22 frames
Streaming lookaheadUnknown4 frames
Supported languagesUnknownChinese, English, French, German, Italian, Japanese, Korean, Portuguese, Russian, Spanish
Target sample rateUnknown24000 Hz

12 comparable fields · 11 material differences · 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

VibeVoice ASR Streaming 7B Capabilities

diarizationhotwordsmultilingualstreamingtranscription
Input price
Output price
Serving providers0
Canonical IDmicrosoft/VibeVoice-ASR-Streaming-7B

Internal Comparison Graph

Related Comparisons

All audio comparisons →
APairBContext
vsdeveloper peerstext

Primary Evidence

Sources and Freshness

Questions

Lyria 3.5 vs VibeVoice ASR Streaming 7B FAQs

Is Lyria 3.5 or VibeVoice ASR Streaming 7B better for coding?+

This comparison does not currently contain a protocol-matched coding benchmark for both Lyria 3.5 and VibeVoice ASR Streaming 7B, so Model Markets cannot name a coding leader from pricing, context size, or capability labels alone.

Which is cheaper, Lyria 3.5 or VibeVoice ASR Streaming 7B?+

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 VibeVoice ASR Streaming 7B?+

Neither model has a larger sourced context window in this comparison. Lyria 3.5 is 1,049K and VibeVoice ASR Streaming 7B is —.

Which performs better in benchmarks, Lyria 3.5 or VibeVoice ASR Streaming 7B?+

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 VibeVoice ASR Streaming 7B be self-hosted?+

VibeVoice ASR Streaming 7B is the only model in this pair currently marked as self-hostable. Lyria 3.5 is not marked open weight; VibeVoice ASR Streaming 7B is open weight.

Can Lyria 3.5 and VibeVoice ASR Streaming 7B understand images?+

Lyria 3.5 is documented with image input; VibeVoice ASR Streaming 7B is not documented with image input. This reflects supported input modalities, not vision quality.

Which can generate longer answers, Lyria 3.5 or VibeVoice ASR Streaming 7B?+

Neither has a larger sourced maximum output. Lyria 3.5 is 66K and VibeVoice ASR Streaming 7B is —.

Do Lyria 3.5 and VibeVoice ASR Streaming 7B support reasoning and tool use?+

Lyria 3.5: image input. VibeVoice ASR Streaming 7B: 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 VibeVoice ASR Streaming 7B?+

Lyria 3.5 has 2 sourced provider routes; VibeVoice ASR Streaming 7B has 0, so Lyria 3.5 has broader tracked availability.

Which offers better value, Lyria 3.5 or VibeVoice ASR Streaming 7B?+

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