VibeVoice ASR Streaming 7B vs Bonsai 27B
At a Glance
| Compare | VibeVoice ASR Streaming 7BMicrosoft | Bonsai 27BPrismML |
|---|---|---|
| Pricing and Limits | ||
| Context windowMaximum documented tokens | Not reported | 262K |
| Model facts checked | Sep 2, 2026View model evidence → | Sep 18, 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-7B | Bonsai 27B |
|---|---|---|
| Developer | Microsoft | PrismML |
| Family | Vibevoice ASR Streaming | Bonsai 27b |
| Model | VibeVoice-ASR-Streaming-7B | Bonsai 27B |
| Version | VibeVoice-ASR-Streaming-7B | Bonsai 27B |
| Lifecycle | active | active |
| Released | 2026-09-03 | 2026-07-04 |
| Knowledge cutoff | Unknown | Unknown |
| Input modalities | Audio | Text, Image |
| Output modalities | Text | Text |
| Context window | Unknown | 262K |
| Total parameters | 8.7B | 27B |
| Active parameters | Unknown | Unknown |
| License | mit | apache-2.0 |
| Open weights | Yes | Yes |
| API available | No | No |
| Self-hostable | Yes | Yes |
| Provider access | Unknown | Unknown |
| Capabilities | diarization, hotwords, multilingual, streaming, transcription | chat, generation, reasoning, tools, vision |
| Base model | Unknown | Qwen3.6 27B |
| Streaming chunk | 22 frames | Unknown |
| Effective bit width | Unknown | 1 bit per weight |
| Language model size | Unknown | 3.53 GiB |
| Streaming lookahead | 4 frames | Unknown |
| Supported languages | Chinese, English, French, German, Italian, Japanese, Korean, Portuguese, Russian, Spanish | Unknown |
| Target sample rate | 24000 Hz | Unknown |
| Weight format | Unknown | Binary Q1_0 |
VibeVoice ASR Streaming 7B Capabilities
Bonsai 27B Capabilities
Primary Evidence
Sources and Freshness
Questions
VibeVoice ASR Streaming 7B vs Bonsai 27B FAQs
Is VibeVoice ASR Streaming 7B or Bonsai 27B better for coding?+
This comparison does not currently contain a protocol-matched coding benchmark for both VibeVoice ASR Streaming 7B and Bonsai 27B, so Model Markets cannot name a coding leader from pricing, context size, or capability labels alone.
Which is cheaper, VibeVoice ASR Streaming 7B or Bonsai 27B?+
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, VibeVoice ASR Streaming 7B or Bonsai 27B?+
Neither model has a larger sourced context window in this comparison. VibeVoice ASR Streaming 7B is — and Bonsai 27B is 262K.
Which performs better in benchmarks, VibeVoice ASR Streaming 7B or Bonsai 27B?+
There is no overall benchmark winner: At least two independently verified, protocol-matched benchmarks are required for an overall winner.
Can VibeVoice ASR Streaming 7B or Bonsai 27B be self-hosted?+
Both models have the same recorded self-hosting status: supported. VibeVoice ASR Streaming 7B is open weight; Bonsai 27B is open weight.
Can VibeVoice ASR Streaming 7B and Bonsai 27B understand images?+
VibeVoice ASR Streaming 7B is not documented with image input; Bonsai 27B is documented with image input. This reflects supported input modalities, not vision quality.
Which can generate longer answers, VibeVoice ASR Streaming 7B or Bonsai 27B?+
Neither has a larger sourced maximum output. VibeVoice ASR Streaming 7B is — and Bonsai 27B is —.
Do VibeVoice ASR Streaming 7B and Bonsai 27B support reasoning and tool use?+
VibeVoice ASR Streaming 7B: none of these features are definitively sourced. Bonsai 27B: reasoning, tool calling, and image input. Feature support does not establish relative quality.
Which is available from more inference providers, VibeVoice ASR Streaming 7B or Bonsai 27B?+
VibeVoice ASR Streaming 7B has 0 sourced provider routes; Bonsai 27B has 0, a tie.
Which offers better value, VibeVoice ASR Streaming 7B or Bonsai 27B?+
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.