← All models

Stable Audio 2.5

Audio Available Full comparison ↗

stability-ai/stable-audio-2-5 · by Stability AI · Diffusion transformer (DiT)

Pricing — 1 offering(s)

Stability AI

View on Stability AI ↗

Per generation

  • $0.20 / generation Historical 2026-06-26 → 2026-10-10
  • $0.08 / generation Current 2026-10-11 → present
    8 credits per generation at $0.01 a credit (Stability pricing page, checked 2026-10-11). Stability cut the…

    8 credits per generation at $0.01 a credit (Stability pricing page, checked 2026-10-11). Stability cut the price from 20 credits ($0.20) between 2026-09-20 and 2026-10-11.

Showing the active price and any recorded history. Full pricing history is available via the paid API — see API docs.

See how Stable Audio 2.5 fits into a cost-aware routing setup

See how →

Capability profile

How Stable Audio 2.5 rates across core capability dimensions, with the task-level evidence behind each rating.

audio quality Strong

High-fidelity stereo output. Improved coherence over 2.0 across instrumental and sound design content.

style range Strong

Broad style coverage from text descriptions. Strong on electronic, ambient, cinematic, and classical genres.

vocal support Weak

Limited vocal generation; designed primarily for instrumental music and sound design.

duration ceiling Strong

Up to 3 minutes per generation with timing conditioning for precise duration control.

audio conditioning Strong

Accepts audio samples as conditioning input alongside text prompts, enabling style transfer and audio continuation.

Operator guidance

The standard-tier current Stable Audio option at $0.20/generation. Choose over deprecated 2.0 for the same price with improved coherence and audio conditioning. Choose 3.0 instead if you need more than 3 minutes per generation ($0.26, up to 6 minutes). For vocals and lyrics, Suno v4 is the better choice. For open-weights self-hosting, MusicGen Large eliminates cost at scale.

Use cases

Limitations

Citations