stable-audio-3

Name: stable-audio-3
Author: Comfy-Org

SpecializedProprietary

Comfy-Org

stable-audio-3 is a proprietary Comfy-Org specialized model.

Model updates refreshed2mo agoJul 30, 2026news + changelog

Website View Updates

Rates & subscription access

View full pricing details

Tracked access rates

Live access is not confirmed for this model. No current purchase price is advertised.

Related provider subscriptions

No current subscription pricing is tracked for this model.

Confirm this specific model, usage limits, and billing terms with the provider. A subscription does not automatically include API credits.

No login needed to compare. Prices are in USD; provider charges are separate from AI Market Cap plans. Context length, caching, tools, taxes, and regional terms can change the final cost. Open weights do not mean free hosting.

---

Quality Score

---

Arena ELO

Undisclosed

Parameters

---

Context

Evidence profile

How complete is this record?

This measures the amount of verifiable public evidence we have, not how capable the model is. A missing field means it has not been verified yet, not that its value is zero.

41%

coverage

Limited evidence

9 of 22 public signals

Technical profile40%

Similar Models

View All

Mistral-Small-3.1-24B-Instruct-2503#586

Mistral AI·24B

54.3

Mistral-Small-4-119B-2603#810

Discussion (0)

Sign in to join the discussion

Loading comments...

122.1K

Downloads

52

Likes

May 2026

Released

2/5 signals

Evaluation0%

0/4 signals

Access & cost40%

2/5 signals

Adoption75%

3/4 signals

Provenance50%

2/4 signals

Gaps we are still tracking

verified descriptionparameter countcontext windowevaluation evidenceverified pricingindependent metadata source

Open Source

1

medium

General

1

low

What Changed Recently

Recent launch, pricing, benchmark, and API signals linked to this model or its provider.

Open SourceStability AI2mo ago

Meet Stable Audio 3.0, the model family built for artistic experimentation with open-weight models

View source

GeneralStability AI

Social & Blog Posts2

BlogStability AIopen_sourceopen source

Mistral AI

·

119B

49.6

Qwen3-TTS-12Hz-1.7B-Base#1430

Qwen·2B

46.0

Nemotron-3-Diarization#5582

NVIDIA·99M

44.9

Mistral-Large-3-675B-Instruct-2512#1676

Mistral AI·675B

44.6

3mo ago

Most AI audio models have never heard a maqam. Team Motif fine-tuned Stable Audio 3.0 on Arabic maqam, built an Ableton plugin for microtonal style transfer, and won our Stable Audio 3.0 Challenge at

Most AI audio models have never heard a maqam. Team Motif fine-tuned Stable Audio 3.0 on Arabic maqam, built an Ableton plugin for microtonal style transfer, and won our Stable Audio 3.0 Challenge at Music Hackspace running locally on device. Watch Jad Al Masri break it down https://t.co/yeFYtY7FbS

View source

2mo ago

Meet Stable Audio 3.0, the model family built for artistic experimentation with open-weight models

View Source

#stability ai#blog#open-source

X/Twitter@StabilityAIStability AIannouncementgeneral3mo ago

Most AI audio models have never heard a maqam. Team Motif fine-tuned Stable Audio 3.0 on Arabic maqam, built an Ableton plugin for microtonal style transfer, and won our Stable Audio 3.0 Challenge at

Most AI audio models have never heard a maqam. Team Motif fine-tuned Stable Audio 3.0 on Arabic maqam, built an Ableton plugin for microtonal style transfer, and won our Stable Audio 3.0 Challenge at Music Hackspace running locally on device. Watch Jad Al Masri break it down https://t.co/yeFYtY7FbS

View Post

#stability ai#twitter#x