Stable Audio 3 Medium Text to Audio
stability-ai/stable-audio/3/medium/text-to-audioStable Audio 3 Medium by Stability AI generates music, ambience and sound design up to about 6 minutes from a text prompt.
- Base price
- $0.04USD / run
- Execution
- async
- Model type
- audio
- Input fields
- 5
Try the model
Playground
Examples
Select an example to load its inputs and result into the playground.
Model card
Specifications
Pricing
- Base price
- $0.04 / run
Context & modalities
- Input
- Schema-defined
- Output
- audio
Capabilities
- Chat
- Not supported
- Vision
- Not supported
- Reasoning
- Not supported
- Structured output
- Not supported
- Function calling
- Not supported
- Audio input
- Not supported
Access
- Provider
- stability-ai
- Model ID
- stability-ai/stable-audio/3/medium/text-to-audio
- Execution
- async
- API
- Unified Run API
- Endpoint
- /v1/run
API README
Stable Audio 3 Medium Text to Audio
Stable Audio 3 Medium by Stability AI generates music, ambience and sound design up to about 6 minutes from a text prompt.
Parameters
| Field | Description |
|---|---|
prompt | Text description (required) |
negative_prompt | Qualities to avoid |
duration | 1–380 seconds, default 30 |
seed | Reproducibility |
output_format | mp3 / wav / flac / ogg / opus / m4a / aac |
Pricing
| Configuration | Price |
|---|---|
| Per generation (any duration) | $0.0376 |
Output: one audio file URL.
Start building
Send your first request
OpenAI-compatible endpoint with unified authentication and usage tracking.
# The quoted heredoc keeps Unicode and shell metacharacters unchanged.
result=$(curl --fail-with-body --silent \
-X POST "https://api.sandbase.ai/v1/run" \
-H "Authorization: Bearer $SANDBASE_API_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'SANDBASE_JSON'
{
"model": "stability-ai/stable-audio/3/medium/text-to-audio",
"prompt": "An anthemic Pop Rock instrumental that fills your head with nostalgic thoughtfulness",
"duration": 30,
"output_format": "mp3"
}
SANDBASE_JSON
)
run_id=$(printf '%s' "$result" | jq -r .id)
for attempt in $(seq 1 120); do
status=$(printf '%s' "$result" | jq -r .status)
case "$status" in completed|failed|timeout) break ;; esac
sleep 2
result=$(curl --fail-with-body --silent \
-H "Authorization: Bearer $SANDBASE_API_KEY" \
"https://api.sandbase.ai/v1/run/$run_id")
done
status=$(printf '%s' "$result" | jq -r .status)
[ "$status" = completed ] || { echo "Generation ended: $status" >&2; exit 1; }
printf '%s\n' "$result"Choose your model
Compare models
| Model | Type | Default price | Released |
|---|---|---|---|
Stable Audio 3 Medium Text to AudioThis model stability-ai | Audio | $0.04 / run | Jun 3, 2026 |
stability-ai | Audio | $0.02 / run | Jun 3, 2026 |
Questions
FAQ
How do I call stability-ai Stable Audio 3 Medium Text to Audio through SandBase?
Create a SandBase API key, then send requests with the model ID "stability-ai/stable-audio/3/medium/text-to-audio" to Unified Run API (/v1/run) at https://api.sandbase.ai. The request examples on this page show the exact payload.
Do I need a separate stability-ai account?
No. One SandBase API key and balance gives you access to stability-ai Stable Audio 3 Medium Text to Audio and the other models in the catalog; you do not need to sign up with stability-ai separately.
