Model reference · open weights
dasheng-audiogen is an open-weight audio or speech model from audiohacking, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.
About
Dasheng-AudioGen GGUF GGUF-converted weights for mispeech/Dasheng-AudioGen Dasheng-AudioGen is a unified audio generation model that can jointly synthesize intelligible speech, music, sound effects, and environmental acoustics from text descriptions. src="https://github.com/user-attachments/assets/497f5688-8731-4830-8ee7-b9cf4234d900" controls autoplay muted loop playsinline width="85%" Model Variants All variants include the same T5 encoder, vocoder, and tokenizer. Files Usage with audiogen.cpp Prompt Format Supports the same prompt tags as the original model: Example: Complex multi-tag prompt Generation Options Performance Original Model This is a GGUF conversion of mispeech/Dasheng-AudioGen. Please refer to the original model card for more details about the model architecture and training. License Apache-2.0 - Same as the original model
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | audiohacking |
|---|---|
| Type | Audio & music |
| Variants | 1 |
| Based on | mispeech/Dasheng-AudioGen |
| Released | 2026-06-23 |
| Popularity | 1k downloads / month |
| Likes | 3 |
| Licence | Open weights |
How it works
Variants
Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.
| Variant | Params | Precision | VRAM | Fits 16 GB | Weights |
|---|---|---|---|---|---|
| dasheng-audiogen-gguf | — | GGUF | — | — | Weights ↗ |
Using it via the API
Once AxForge deploys dasheng-audiogen for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (dasheng-audiogen below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/audio/transcriptions \ -H "Authorization: Bearer $AXFORGE_API_KEY" \ -F model="dasheng-audiogen" -F file=@audio.mp3
Details
Tags
Licence
Open weights under apache-2.0 — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗