> ## Documentation Index
> Fetch the complete documentation index at: https://docs.rawchunks.space/llms.txt
> Use this file to discover all available pages before exploring further.

# Models and their jobs

> The audio, language, vision, transcription and artwork models used by Rawchunks.

Rawchunks assigns each model a specific job. Audio generation runs on L4 workers. Songwriter and Composer use hosted language models; speech and image models prepare their inputs or related assets.

## Music and separation

| Model | Use |
| - | - |
| `acestep-v15-xl-turbo` | **FAST** generation, eight diffusion steps and guidance 1. Also serves the edits that support Turbo. |
| `acestep-v15-xl-sft` | **MASTER** generation, 50 diffusion steps and guidance 7. Also serves the edits that support SFT. |
| `acestep-v15-xl-base` | Layering, accompaniment, instrument extraction and Base editing. |
| `acestep-5Hz-lm-0.6B` | ACE-Step's music language model, served through vLLM. Prepares music codes and descriptions used by the audio pipeline. The training configuration also selects this model. |
| `Qwen3-Embedding-0.6B` | Text conditioning for ACE-Step. |
| Demucs `htdemucs` | Separates vocals, drums, bass and other audio. Uses zero shifts and 0.1 overlap. |

Read [music options](https://docs.rawchunks.space/dev/endpoints/system/options.md) for the modes supported by each edit. A Layer or Accompany request uses Base; Rework, Extend and Restyle expose their supported alternatives.

## Language and vision

| Model | Use |
| - | - |
| `nvidia/Nemotron-3-Ultra-550b-a55b` | Songwriter's planning and lyric streams; Composer's graph-guided tool calls and pattern repair. Served by Nebius Token Factory. |
| `nvidia/Nemotron-3.5-Super-VL` | Converts an image's mood, theme and visual context into a musical brief for Songwriter. Served by Nebius Token Factory. |

[Songwriter](https://docs.rawchunks.space/ai-ml/songwriter.md) and [Composer](https://docs.rawchunks.space/ai-ml/composer.md) explain the context and outputs for each agent.

## Speech and artwork

| Model | Use |
| - | - |
| Cartesia `ink-whisper` | Primary transcription for spoken or sung Vibe recordings. |
| ElevenLabs `scribe_v2` | Fallback Vibe transcription and Editor vocal transcription. ElevenLabs forced alignment places supplied lyrics against the recording. |
| Google `gemini-nano-banana-2.1` | Generates separate song-cover artwork from the brief, title and style. The cover prompt uses Rawchunks' black, acid-green, magenta and cyan palette. |

Vibe audio also goes through local signal analysis, so a hum can supply musical information without transcribed words. [Saved voices](https://docs.rawchunks.space/ai-ml/voices.md) use ACE-Step reference conditioning and LoRA preparation.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.