higurashiAudio modelWeights available
Haru-4B
34out of 100first value
usage data only, range 20 to 48
Summary
Haru-4B is a higurashi full-duplex speech model for continuous audio conversations. It processes and generates speech with accompanying text output. The research model supports nine languages, including German, English and Japanese.
Weights and inference code are publicly available. The weights use Apache 2.0. A reference recording can condition the voice, and audio processing uses 24 kHz.
On this page
Popularity compared
How often the model is searched for, used and mentioned, compared with every model of its category.
Popularity index
0 to 100, higher is more popular
20 of 54 models
As of November 2026 · Source: gradually.ai popularity index
Over time
Weekly values from November 15, 2026 to November 20, 2026
Haru-4BGemini 3.5 Transcribe Live 35GPT-Realtime-Whisper 34Granite Speech 5.0 470M TurboCTC 33GPT-4o Mini Transcribe 33
What is gaining popularity right now, across models, vendors, harnesses and AI subscriptions, is collected in All AI trends.
Similar models
More models of the same kind as Haru-4B, chosen by model line, developer, size, price and release date.
- MOSS-Audio-4B-ThinkingOpenMOSS Team · similar size
- Maya 2 NativeMaya Research · similar size
- LFM3-Audio-2BLiquid AI · similar size
- Voxtral Mini Transcribe 3Mistral AI · similar size
- NVIDIA Nemotron 3.5 TranscribeNVIDIA · released around the same time
- YuE2-3Bm-a-p · similar size
- OrukeetOruk · released around the same time
- Nemotron-3-DiarizationNVIDIA · released around the same time
All specifications
Architecture
- Parameters
- The released weights contain 5,270,000,897 BF16 parameters. “4B” refers to the Qwen3.5-4B text backbone.
- Source: Parameters
Input and output
- Languages
- English, Spanish, Portuguese, German, French, Chinese, Japanese, Russian, and Korean
- Source: Languages
- Text backbone configuration
- The Qwen text configuration lists 262,144 positions. This is not a published end-to-end context limit for audio dialogue.
- Source: Text backbone configuration
Watermarking and provenance
AI watermarking refers to invisible signals embedded in the output. Visible marks and provenance metadata are listed separately. Unknown means there is insufficient evidence for that particular field.
- AI watermarking
- Unknown
- no source
- Watermarking technique
- Not known
- no source
Licence and access
- Access
- Public weights and inference code for local use; the reviewed model card lists no hosted inference provider.
- Source: Access
- Shutdown
- None announced
- no source
Further details
- Audio frames
- 24 kHz, 3,200 samples per frame, and 7.5 frames per second (133 ms).
- Source: Audio frames
Sources and data date
Show all 11 sources
| Type | Evidence and data date |
|---|---|
| Additional source | Haru-4B model card (retrieved November 14, 2026) · Haru-4B model card · Editorial description reviewed November 14, 2026 |
| Additional source | Haru-4B model metadata (retrieved November 14, 2026) |
| Additional source | Haru-4B text and audio configuration (retrieved November 14, 2026) |
| Additional source | higurashi Haru-4B release article (retrieved November 14, 2026) · higurashi Haru-4B release · Editorial description reviewed November 14, 2026 |
| Additional source | Haru inference code (retrieved November 14, 2026) |
| Additional source | OpenRouter: Popularity index (derived), CC BY 4.0 |
| Additional source | Vercel AI Gateway: Popularity index (derived), CC BY 4.0 |
| Additional source | Ollama: cumulative downloads for the popularity index |
| Additional source | Replicate: cumulative runs for the popularity index |
| Additional source | Google Trending Now: limited feed selection for Germany and the US |
| Additional source | Creative Commons Attribution 4.0 |