AI model comparison

VibeVoice ASR Streaming 1.5B vs VibeVoice ASR Streaming 7B

Compare pricing, context limits, supported inputs and deployment options to choose a model for your workflow.

Both VibeVoice Streaming ASR checkpoints produce speaker-attributed transcription, support ten languages and accept hotwords. Their names describe different language backbones; complete speech checkpoints also include audio components.

Side-by-sideCapabilities and practical differences

Microsoft Research

VibeVoice ASR Streaming 1.5B

VibeVoice ASR Streaming 1.5B transcribes incoming speech with speaker attribution, custom hotwords and support for ten languages.

Accepts

  • Audio input

Produces

  • Text output
VS

Microsoft Research

VibeVoice ASR Streaming 7B

VibeVoice ASR Streaming 7B transcribes incoming speech with speaker attribution, custom hotwords and support for ten languages.

Accepts

  • Audio input

Produces

  • Text output

Specifications

Pricing, limits and capabilities

Specifications for VibeVoice ASR Streaming 1.5B and VibeVoice ASR Streaming 7B. Higher limits and lower prices describe these figures only.
SpecificationVibeVoice ASR Streaming 1.5BVibeVoice ASR Streaming 7B
ProviderMicrosoft ResearchMicrosoft Research
Listed pricing routeMicrosoft ResearchMicrosoft Research
Model family——
Accepted inputsaudioaudio
Produced outputstexttext
Reasoning modeNot documentedNot documented
Tool callingNot documentedNot documented
Image inputNot documentedNot documented
Audio inputDocumentedDocumented
Structured outputNot documentedNot documented
LicenseMITMIT

Workload guidance

Which model should you choose?

Test 1.5B first when memory and response time matter. Compare 7B on the names, accents and overlapping turns in your recordings. Judge transcript accuracy and speaker assignment separately, and choose the larger model only if its measured improvement justifies the operating footprint.

Documentation and model profiles

Explore each model’s features, API requirements and licence terms in the sources below.

Questions people ask

It brings together documented inputs and outputs, token limits, deployment terms and available pricing. When both models have source-linked, verified results on a shared benchmark, those results are shown with their individual sources. The comparison is a starting point for evaluating your own workload.

Compare a different pair

Search by model or provider to explore another comparison.

Open model comparison