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
AI model comparison
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.
Microsoft Research
VibeVoice ASR Streaming 1.5B transcribes incoming speech with speaker attribution, custom hotwords and support for ten languages.
Accepts
Produces
Microsoft Research
VibeVoice ASR Streaming 7B transcribes incoming speech with speaker attribution, custom hotwords and support for ten languages.
Accepts
Produces
Specifications
| Specification | VibeVoice ASR Streaming 1.5B | VibeVoice ASR Streaming 7B |
|---|---|---|
| Provider | Microsoft Research | Microsoft Research |
| Listed pricing route | Microsoft Research | Microsoft Research |
| Model family | — | — |
| Accepted inputs | audio | audio |
| Produced outputs | text | text |
| Reasoning mode | Not documented | Not documented |
| Tool calling | Not documented | Not documented |
| Image input | Not documented | Not documented |
| Audio input | Documented | Documented |
| Structured output | Not documented | Not documented |
| License | MIT | MIT |
Workload guidance
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.
Explore each model’s features, API requirements and licence terms in the sources below.
VibeVoice ASR Streaming 1.5B
Microsoft Research
Profile updated Oct 8, 2026
VibeVoice ASR Streaming 7B
Microsoft Research
Profile updated Oct 8, 2026
Search by model or provider to explore another comparison.