AudioCraft Audio Generation with Hermes Agent: MusicGen, AudioGen, EnCodec

AudioCraft brings Meta's MusicGen, AudioGen, and EnCodec models into Hermes Agent as an optional creative skill. You can generate music from text, produce sound effects, condition output on a melody or style reference, and compress audio with a neural codec. This guide covers installation, every generation mode, common workflows, and performance tuning.

What it does

AudioCraft wraps three model families. MusicGen turns text descriptions into music, with optional melody conditioning and style transfer. AudioGen generates sound effects and environmental audio from text. EnCodec compresses audio into discrete tokens and reconstructs it. All models run locally, so you control latency and privacy.

Before you start

This skill is optional and installed on demand. It runs on Linux and macOS. The skill path is optional-skills/creative/audiocraft-audio-generation. You need Python and pip. The larger models require significant GPU memory: musicgen-small needs about 4 GB in FP32, musicgen-medium needs 8 GB, and musicgen-large needs 16 GB. Half-precision (FP16) roughly halves those numbers. You also need torchaudio and, for the HuggingFace Transformers path, scipy.

Install the core library:

# From PyPI
pip install audiocraft

# From GitHub (latest)
pip install git+https://github.com/facebookresearch/audiocraft.git

# Or use HuggingFace Transformers
pip install transformers torch torchaudio

Quick start

Basic text-to-music (AudioCraft)

import torchaudio
from audiocraft.models import MusicGen

# Load model
model = MusicGen.get_pretrained('facebook/musicgen-small')

# Set generation parameters
model.set_generation_params(
    duration=8,  # seconds
    top_k=250,
    temperature=1.0
)

# Generate from text
descriptions = ["happy upbeat electronic dance music with synths"]
wav = model.generate(descriptions)

# Save audio
torchaudio.save("output.wav", wav[0].cpu(), sample_rate=32000)

Using HuggingFace Transformers

from transformers import AutoProcessor, MusicgenForConditionalGeneration
import scipy

# Load model and processor
processor = AutoProcessor.from_pretrained("facebook/musicgen-small")
model = MusicgenForConditionalGeneration.from_pretrained("facebook/musicgen-small")
model.to("cuda")

# Generate music
inputs = processor(
    text=["80s pop track with bassy drums and synth"],
    padding=True,
    return_tensors="pt"
).to("cuda")

audio_values = model.generate(
    **inputs,
    do_sample=True,
    guidance_scale=3,
    max_new_tokens=256
)

# Save
sampling_rate = model.config.audio_encoder.sampling_rate
scipy.io.wavfile.write("output.wav", rate=sampling_rate, data=audio_values[0, 0].cpu().numpy())

Text-to-sound with AudioGen

from audiocraft.models import AudioGen

# Load AudioGen
model = AudioGen.get_pretrained('facebook/audiogen-medium')

model.set_generation_params(duration=5)

# Generate sound effects
descriptions = ["dog barking in a park with birds chirping"]
wav = model.generate(descriptions)

torchaudio.save("sound.wav", wav[0].cpu(), sample_rate=16000)

Core concepts

Architecture overview

AudioCraft Architecture:
┌──────────────────────────────────────────────────────────────┐
│                    Text Encoder (T5)                          │
│                         │                                     │
│                    Text Embeddings                            │
└────────────────────────┬─────────────────────────────────────┘
                         │
┌────────────────────────▼─────────────────────────────────────┐
│              Transformer Decoder (LM)                         │
│     Auto-regressively generates audio tokens                  │
│     Using efficient token interleaving patterns               │
└────────────────────────┬─────────────────────────────────────┘
                         │
┌────────────────────────▼─────────────────────────────────────┐
│                EnCodec Audio Decoder                          │
│        Converts tokens back to audio waveform                 │
└──────────────────────────────────────────────────────────────┘

Model variants

Model	Size	Description	Use Case
musicgen-small	300M	Text-to-music	Quick generation
musicgen-medium	1.5B	Text-to-music	Balanced
musicgen-large	3.3B	Text-to-music	Best quality
musicgen-melody	1.5B	Text + melody	Melody conditioning
musicgen-melody-large	3.3B	Text + melody	Best melody
musicgen-stereo-*	Varies	Stereo output	Stereo generation
musicgen-style	1.5B	Style transfer	Reference-based
audiogen-medium	1.5B	Text-to-sound	Sound effects

Generation parameters

Parameter	Default	Description
duration	8.0	Length in seconds (1-120)
top_k	250	Top-k sampling
top_p	0.0	Nucleus sampling (0 = disabled)
temperature	1.0	Sampling temperature
cfg_coef	3.0	Classifier-free guidance

MusicGen usage

Text-to-music generation

from audiocraft.models import MusicGen
import torchaudio

model = MusicGen.get_pretrained('facebook/musicgen-medium')

# Configure generation
model.set_generation_params(
    duration=30,          # Up to 30 seconds
    top_k=250,            # Sampling diversity
    top_p=0.0,            # 0 = use top_k only
    temperature=1.0,      # Creativity (higher = more varied)
    cfg_coef=3.0          # Text adherence (higher = stricter)
)

# Generate multiple samples
descriptions = [
    "epic orchestral soundtrack with strings and brass",
    "chill lo-fi hip hop beat with jazzy piano",
    "energetic rock song with electric guitar"
]

# Generate (returns [batch, channels, samples])
wav = model.generate(descriptions)

# Save each
for i, audio in enumerate(wav):
    torchaudio.save(f"music_{i}.wav", audio.cpu(), sample_rate=32000)

Melody-conditioned generation

from audiocraft.models import MusicGen
import torchaudio

# Load melody model
model = MusicGen.get_pretrained('facebook/musicgen-melody')
model.set_generation_params(duration=30)

# Load melody audio
melody, sr = torchaudio.load("melody.wav")

# Generate with melody conditioning
descriptions = ["acoustic guitar folk song"]
wav = model.generate_with_chroma(descriptions, melody, sr)

torchaudio.save("melody_conditioned.wav", wav[0].cpu(), sample_rate=32000)

Stereo generation

from audiocraft.models import MusicGen

# Load stereo model
model = MusicGen.get_pretrained('facebook/musicgen-stereo-medium')
model.set_generation_params(duration=15)

descriptions = ["ambient electronic music with wide stereo panning"]
wav = model.generate(descriptions)

# wav shape: [batch, 2, samples] for stereo
print(f"Stereo shape: {wav.shape}")  # [1, 2, 480000]
torchaudio.save("stereo.wav", wav[0].cpu(), sample_rate=32000)

Audio continuation

from transformers import AutoProcessor, MusicgenForConditionalGeneration

processor = AutoProcessor.from_pretrained("facebook/musicgen-medium")
model = MusicgenForConditionalGeneration.from_pretrained("facebook/musicgen-medium")

# Load audio to continue
import torchaudio
audio, sr = torchaudio.load("intro.wav")

# Process with text and audio
inputs = processor(
    audio=audio.squeeze().numpy(),
    sampling_rate=sr,
    text=["continue with a epic chorus"],
    padding=True,
    return_tensors="pt"
)

# Generate continuation
audio_values = model.generate(**inputs, do_sample=True, guidance_scale=3, max_new_tokens=512)

MusicGen-Style usage

Style-conditioned generation

from audiocraft.models import MusicGen

# Load style model
model = MusicGen.get_pretrained('facebook/musicgen-style')

# Configure generation with style
model.set_generation_params(
    duration=30,
    cfg_coef=3.0,
    cfg_coef_beta=5.0  # Style influence
)

# Configure style conditioner
model.set_style_conditioner_params(
    eval_q=3,          # RVQ quantizers (1-6)
    excerpt_length=3.0  # Style excerpt length
)

# Load style reference
style_audio, sr = torchaudio.load("reference_style.wav")

# Generate with text + style
descriptions = ["upbeat dance track"]
wav = model.generate_with_style(descriptions, style_audio, sr)

Style-only generation (no text)

# Generate matching style without text prompt
model.set_generation_params(
    duration=30,
    cfg_coef=3.0,
    cfg_coef_beta=None  # Disable double CFG for style-only
)

wav = model.generate_with_style([None], style_audio, sr)

AudioGen usage

Sound effect generation

from audiocraft.models import AudioGen
import torchaudio

model = AudioGen.get_pretrained('facebook/audiogen-medium')
model.set_generation_params(duration=10)

# Generate various sounds
descriptions = [
    "thunderstorm with heavy rain and lightning",
    "busy city traffic with car horns",
    "ocean waves crashing on rocks",
    "crackling campfire in forest"
]

wav = model.generate(descriptions)

for i, audio in enumerate(wav):
    torchaudio.save(f"sound_{i}.wav", audio.cpu(), sample_rate=16000)

EnCodec usage

Audio compression

from audiocraft.models import CompressionModel
import torch
import torchaudio

# Load EnCodec
model = CompressionModel.get_pretrained('facebook/encodec_32khz')

# Load audio
wav, sr = torchaudio.load("audio.wav")

# Ensure correct sample rate
if sr != 32000:
    resampler = torchaudio.transforms.Resample(sr, 32000)
    wav = resampler(wav)

# Encode to tokens
with torch.no_grad():
    encoded = model.encode(wav.unsqueeze(0))
    codes = encoded[0]  # Audio codes

# Decode back to audio
with torch.no_grad():
    decoded = model.decode(codes)

torchaudio.save("reconstructed.wav", decoded[0].cpu(), sample_rate=32000)

Common workflows

Workflow 1: Music generation pipeline

import torch
import torchaudio
from audiocraft.models import MusicGen

class MusicGenerator:
    def __init__(self, model_name="facebook/musicgen-medium"):
        self.model = MusicGen.get_pretrained(model_name)
        self.sample_rate = 32000

    def generate(self, prompt, duration=30, temperature=1.0, cfg=3.0):
        self.model.set_generation_params(
            duration=duration,
            top_k=250,
            temperature=temperature,
            cfg_coef=cfg
        )

        with torch.no_grad():
            wav = self.model.generate([prompt])

        return wav[0].cpu()

    def generate_batch(self, prompts, duration=30):
        self.model.set_generation_params(duration=duration)

        with torch.no_grad():
            wav = self.model.generate(prompts)

        return wav.cpu()

    def save(self, audio, path):
        torchaudio.save(path, audio, sample_rate=self.sample_rate)

# Usage
generator = MusicGenerator()
audio = generator.generate(
    "epic cinematic orchestral music",
    duration=30,
    temperature=1.0
)
generator.save(audio, "epic_music.wav")

Workflow 2: Sound design batch processing

import json
from pathlib import Path
from audiocraft.models import AudioGen
import torchaudio

def batch_generate_sounds(sound_specs, output_dir):
    """
    Generate multiple sounds from specifications.

    Args:
        sound_specs: list of {"name": str, "description": str, "duration": float}
        output_dir: output directory path
    """
    model = AudioGen.get_pretrained('facebook/audiogen-medium')
    output_dir = Path(output_dir)
    output_dir.mkdir(exist_ok=True)

    results = []

    for spec in sound_specs:
        model.set_generation_params(duration=spec.get("duration", 5))

        wav = model.generate([spec["description"]])

        output_path = output_dir / f"{spec['name']}.wav"
        torchaudio.save(str(output_path), wav[0].cpu(), sample_rate=16000)

        results.append({
            "name": spec["name"],
            "path": str(output_path),
            "description": spec["description"]
        })

    return results

# Usage
sounds = [
    {"name": "explosion", "description": "massive explosion with debris", "duration": 3},
    {"name": "footsteps", "description": "footsteps on wooden floor", "duration": 5},
    {"name": "door", "description": "wooden door creaking and closing", "duration": 2}
]

results = batch_generate_sounds(sounds, "sound_effects/")

Workflow 3: Gradio demo

import gradio as gr
import torch
import torchaudio
from audiocraft.models import MusicGen

model = MusicGen.get_pretrained('facebook/musicgen-small')

def generate_music(prompt, duration, temperature, cfg_coef):
    model.set_generation_params(
        duration=duration,
        temperature=temperature,
        cfg_coef=cfg_coef
    )

    with torch.no_grad():
        wav = model.generate([prompt])

    # Save to temp file
    path = "temp_output.wav"
    torchaudio.save(path, wav[0].cpu(), sample_rate=32000)
    return path

demo = gr.Interface(
    fn=generate_music,
    inputs=[
        gr.Textbox(label="Music Description", placeholder="upbeat electronic dance music"),
        gr.Slider(1, 30, value=8, label="Duration (seconds)"),
        gr.Slider(0.5, 2.0, value=1.0, label="Temperature"),
        gr.Slider(1.0, 10.0, value=3.0, label="CFG Coefficient")
    ],
    outputs=gr.Audio(label="Generated Music"),
    title="MusicGen Demo"
)

demo.launch()

Performance optimization

Memory optimization

# Use smaller model
model = MusicGen.get_pretrained('facebook/musicgen-small')

# Clear cache between generations
torch.cuda.empty_cache()

# Generate shorter durations
model.set_generation_params(duration=10)  # Instead of 30

# Use half precision
model = model.half()

Batch processing efficiency

# Process multiple prompts at once (more efficient)
descriptions = ["prompt1", "prompt2", "prompt3", "prompt4"]
wav = model.generate(descriptions)  # Single batch

# Instead of
for desc in descriptions:
    wav = model.generate([desc])  # Multiple batches (slower)

GPU memory requirements

Model	FP32 VRAM	FP16 VRAM
musicgen-small	~4GB	~2GB
musicgen-medium	~8GB	~4GB
musicgen-large	~16GB	~8GB

Common issues

Issue	Solution
CUDA OOM	Use smaller model, reduce duration
Poor quality	Increase cfg_coef, better prompts
Generation too short	Check max duration setting
Audio artifacts	Try different temperature
Stereo not working	Use stereo model variant

When not to use it

AudioCraft is not the only option. If you need longer commercial music generation, Stable Audio may be a better fit. For text-to-speech with music or sound effects, look at Bark. Riffusion offers spectrogram-based music generation. OpenAI Jukebox handles raw audio generation with lyrics. Each has different strengths in quality, length, and licensing.

Limits and gotchas

Generation quality depends heavily on prompt engineering. A vague prompt produces mediocre output. The models have a maximum duration of 120 seconds, and longer generations use more memory. Audio artifacts can appear at extreme temperature values. Stereo output requires a stereo model variant; using a mono model will not produce stereo audio. The style model's cfg_coef_beta parameter controls style influence, and setting it to None disables double CFG for style-only generation.

Related skills

This skill pairs well with heartmula and songwriting-and-ai-music, which are also in the Hermes Agent optional skills catalog. The references directory in the skill path includes an advanced usage guide covering training, fine-tuning, and deployment, plus a troubleshooting reference for common issues.