GGUF conversions of stabilityai/stable-audio-3-medium for **sa3.cpp** — a portable C++/GGML port of Stable Audio 3, no PyTorch in the loop. Runs on CPU, CUDA, Vulkan, or Metal (Apple Silicon). Every component is validated against the PyTorch reference at cosine similarity ~1.0. This is a multi-file model. Grab the **DiT** + **SAME** at your chosen precision and the **conditioner**, plus the shared **encoder + tokenizer** from the t5gemma-b-b-ul2-GGUF repo. **F16** is the production path (~3.5s for 12s of audio on an 8GB laptop GPU); **F32** is for CPU validation. The conditioner + encoder + tokenizer stay F32 (small / quality-critical).

Speech synthesis

Input Text→ Output Audio

Price not verifiedCheck multimodal and channel pricing separately

View details ↗

CompareSource / docs ↗

stable-audio-3-small-music-GGUF

thepatch

基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。

Basic profile indexed · More details to follow

Speech synthesis

Input Text→ Output Audio

Price not verifiedCheck multimodal and channel pricing separately

View details ↗

CompareSource / docs ↗

stable-audio-3-small-sfx-GGUF

thepatch

基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。

Basic profile indexed · More details to follow

Speech synthesis

Input Text→ Output Audio

Price not verifiedCheck multimodal and channel pricing separately

View details ↗

CompareSource / docs ↗

stable-audio-open-1.0-GGUF

thepatch

基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。

Basic profile indexed · More details to follow

Category pending

Input Not verified→ Output Not verified

Price not verifiedCheck multimodal and channel pricing separately

View details ↗

CompareSource / docs ↗

stable-audio-open-small-GGUF

thepatch

基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。

Basic profile indexed · More details to follow

Category pending

Input Not verified→ Output Not verified

Price not verifiedCheck multimodal and channel pricing separately

View details ↗

CompareSource / docs ↗

t5gemma-b-b-ul2-GGUF

thepatch

The **shared** text encoder + tokenizer for **sa3.cpp**. GGUF conversion of the frozen google/t5gemma-b-b-ul2 encoder (encoder-only at inference) that Stable Audio 3 uses to embed text prompts. This component is **identical across all three SA3 variants** (medium, small-music, small-sfx), so it lives in its own repo and is fetched once — the per-variant conditioner ships separately in each model repo. Validated against the PyTorch reference at cosine similarity ~1.0. `F16` is what `sa3.cpp` downloads and resolves by default, and it is a size win rather than a fidelity substitution. `Q8_0` is offered for tight-memory installs; it is a small but real tradeoff, so it is never auto-selected — ask for it by name.

Speech synthesis

Input Text→ Output Audio

Price not verifiedCheck multimodal and channel pricing separately

View details ↗

CompareSource / docs ↗

uvr-vr-GGUF

thepatch

基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。

Basic profile indexed · More details to follow

Audio processing

Input Audio→ Output Audio

Price not verifiedCheck multimodal and channel pricing separately

View details ↗

CompareSource / docs ↗

YuE2-3B-GGUF

thepatch

基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。

Basic profile indexed · More details to follow

Speech synthesis

Input Text→ Output Audio

Price not verifiedCheck multimodal and channel pricing separately

View details ↗

CompareSource / docs ↗

COST EXPLORER

Great models. Clear costs.

Cost analysis

Adjust monthly token usage to compare estimated API costs.

Monthly input tokens 10 MMonthly output tokens 2 M1 M = 1 million tokens · USD
Compares base text-token rates within the same channel

Uses collected, comparable USD-per-million-token rates. Snapshots exclude cache discounts, tiers, extra reasoning output and taxes. Check current source prices.

MODEL HANDBOOK

Understand before you choose

Selection guide & FAQ

How should API prices be compared?+

Separate input, output and cache rates, then estimate the same workload. Image, audio and video rates may use items, duration or resolution rather than tokens.

Do open weights mean free commercial use?+

Not necessarily. Check each version’s license, commercial restrictions and policies. Self-hosting also incurs compute and maintenance costs.

Is the top-ranked model the best for me?+

Rankings depend on tasks, versions and methods. Compare accuracy, latency, reliability and costs on your own workload.

Find your ideal AI model.

Explore AI models 10

htdemucs-GGUF

mdx23c-drumsep-GGUF

stable-audio-3-medium-GGUF

stable-audio-3-small-music-GGUF

stable-audio-3-small-sfx-GGUF

stable-audio-open-1.0-GGUF

stable-audio-open-small-GGUF

t5gemma-b-b-ul2-GGUF

uvr-vr-GGUF

YuE2-3B-GGUF

No matching models

Great models. Clear costs.

Understand before you choose

Follow trends. Find tools. Explore models.