VibeVoice ASR Streaming 1.5B vs phi-4
At a Glance
| Compare |  VibeVoice ASR Streaming 1.5BMicrosoft | phi-4Microsoft |
|---|---|---|
| Pricing and Limits | ||
| Input priceFrom · USD / 1M tokens | Not reported | $0.070Deepinfra ↗ · Sep 22, 2026 |
| Output priceFrom · USD / 1M tokens | Not reported | $0.14Deepinfra ↗ · Sep 22, 2026 |
| Context windowMaximum documented tokens | Not reported | 16K |
| Model facts checked | Sep 2, 2026View model evidence → | Aug 28, 2026View model evidence → |
Token prices are the lowest available sourced USD rates; input and output may use different providers. Cost ranking estimates output spend on LiveBench, not a full request bill. Ranking methodology →
Available Benchmarks
Side-by-Side Facts
| Field | VibeVoice-ASR-Streaming-1.5B | phi-4 |
|---|---|---|
| Developer | Microsoft | Microsoft |
| Family | Vibevoice ASR Streaming | Phi 4 |
| Model | VibeVoice-ASR-Streaming-1.5B | phi-4 |
| Version | VibeVoice-ASR-Streaming-1.5B | phi-4 |
| Lifecycle | active | active |
| Released | 2026-09-03 | 2024-12-12 |
| Knowledge cutoff | Unknown | Unknown |
| Input modalities | Audio | Text |
| Output modalities | Text | Text |
| Context window | Unknown | 16K |
| Total parameters | 2.8B | 14.7B |
| Active parameters | Unknown | Unknown |
| License | mit | mit |
| Open weights | Yes | Yes |
| API available | No | Yes |
| Self-hostable | Yes | Yes |
| Provider access | Unknown | Deepinfra (Standard), Hugging Face (Standard), Openrouter (Standard) |
| Capabilities | diarization, hotwords, multilingual, streaming, transcription | chat, generation |
| Streaming chunk | 22 frames | Unknown |
| Streaming lookahead | 4 frames | Unknown |
| Supported languages | Chinese, English, French, German, Italian, Japanese, Korean, Portuguese, Russian, Spanish | Unknown |
| Target sample rate | 24000 Hz | Unknown |
VibeVoice ASR Streaming 1.5B Capabilities
phi-4 Capabilities
Related Comparisons
All text comparisons →| A | Pair | B | Context |
|---|---|---|---|
VibeVoice-ASR-Streaming-1.5BMicrosoft | vs |  GPT-6 AstraOpenAI | cross-developer peerstext |
Claude Fable 5.1Anthropic | vs | VibeVoice-ASR-Streaming-1.5BMicrosoft | cross-developer peerstext |
 Gemini 3.1 ProGoogle DeepMind | vs | VibeVoice-ASR-Streaming-1.5BMicrosoft | cross-developer peerstext |
 DeepSeek-V4.1-FlashDeepSeek | vs | VibeVoice-ASR-Streaming-1.5BMicrosoft | cross-developer peerstext |
VibeVoice-ASR-Streaming-1.5BMicrosoft | vs | Grok 4.6xAI | cross-developer peerstext |
VibeVoice-ASR-Streaming-1.5BMicrosoft | vs |  Qwen3.8-MaxQwen | cross-developer peerstext |
VibeVoice-ASR-Streaming-1.5BMicrosoft | vs |  Kimi-K3Moonshot AI | cross-developer peerstext |
 MiniMax-M3MiniMax | vs | VibeVoice-ASR-Streaming-1.5BMicrosoft | cross-developer peerstext |
VibeVoice-ASR-Streaming-1.5BMicrosoft | vs |  GLM-5.3Z.ai | cross-developer peerstext |
VibeVoice-ASR-Streaming-1.5BMicrosoft | vs |  Hy4 previewTencent | cross-developer peerstext |
Seed 2.1 ProByteDance Seed | vs | VibeVoice-ASR-Streaming-1.5BMicrosoft | cross-developer peerstext |
VibeVoice-ASR-Streaming-1.5BMicrosoft | vs |  Mistral Large 3Mistral AI | cross-developer peerstext |
Primary Evidence
Sources and Freshness
Questions
VibeVoice ASR Streaming 1.5B vs phi-4 FAQs
Is VibeVoice ASR Streaming 1.5B or phi-4 better for coding?+
This comparison does not currently contain a protocol-matched coding benchmark for both VibeVoice ASR Streaming 1.5B and phi-4, so Model Markets cannot name a coding leader from pricing, context size, or capability labels alone.
Which is cheaper, VibeVoice ASR Streaming 1.5B or phi-4?+
Only phi-4 has a directly sourced input price: $0.070 per million tokens. Only phi-4 has a directly sourced output price: $0.14 per million tokens.
Which has a larger context window, VibeVoice ASR Streaming 1.5B or phi-4?+
Neither model has a larger sourced context window in this comparison. VibeVoice ASR Streaming 1.5B is — and phi-4 is 16K.
Which performs better in benchmarks, VibeVoice ASR Streaming 1.5B or phi-4?+
There is no overall benchmark winner: At least two independently verified, protocol-matched benchmarks are required for an overall winner.
Can VibeVoice ASR Streaming 1.5B or phi-4 be self-hosted?+
Both models have the same recorded self-hosting status: supported. VibeVoice ASR Streaming 1.5B is open weight; phi-4 is open weight.
Can VibeVoice ASR Streaming 1.5B and phi-4 understand images?+
VibeVoice ASR Streaming 1.5B is not documented with image input; phi-4 is not documented with image input. This reflects supported input modalities, not vision quality.
Which can generate longer answers, VibeVoice ASR Streaming 1.5B or phi-4?+
Neither has a larger sourced maximum output. VibeVoice ASR Streaming 1.5B is — and phi-4 is —.
Do VibeVoice ASR Streaming 1.5B and phi-4 support reasoning and tool use?+
VibeVoice ASR Streaming 1.5B: none of these features are definitively sourced. phi-4: none of these features are definitively sourced. Feature support does not establish relative quality.
Which is available from more inference providers, VibeVoice ASR Streaming 1.5B or phi-4?+
VibeVoice ASR Streaming 1.5B has 0 sourced provider routes; phi-4 has 3, so phi-4 has broader tracked availability.
Which offers better value, VibeVoice ASR Streaming 1.5B or phi-4?+
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.