Model reference · open weights

dasheng-audiogen

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.

Audio audiohacking 1 variants 1k downloads/mo
Request this model on EU hardware All served models Not on the shared API today — deployed on request.

About

What dasheng-audiogen is

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

What it is

Makeraudiohacking
TypeAudio & music
Variants1
Based onmispeech/Dasheng-AudioGen
Released2026-06-23
Popularity1k downloads / month
Likes3
LicenceOpen weights

How it works

How audio & music work

Audio or textinputAudio modelrecognise / synthesiseText or audiooutputSpeech-to-text turns audio into text; text-to-speech and music models turn text into audio.

Variants

Sizes & precisions

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.

VariantParamsPrecisionVRAMFits 16 GBWeights
dasheng-audiogen-ggufGGUFWeights ↗

Using it via the API

Call it like any OpenAI endpoint

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

Languages, data & research

Tags

gguf audio text-to-audio ggml

Licence

Open weights

Open weights under apache-2.0 — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗

Sources

Weights & code

Want dasheng-audiogen on EU-owned hardware?

Request this model on EU hardware See what’s served now

Explore

More audio & music

© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms