Cookie Preferences
We use cookies to personalize content and analyze traffic. See our Cookie Policy.
No audio yet. Submit the form to generate audio.
Transparent pricing with no hidden fees. Pay as you go.
| Rule & Modality | Channel | Credits | Price (USD) | Official / Reference Price | Daily Savings |
|---|---|---|---|---|---|
Suno sounds musicSuno | Starter | 1per run | $0.005 | - | - |
Complete guide to using Suno
Use the Suno Sounds API on ApiPass to generate sound effects and ambient audio from text prompts. Submit asynchronous generation tasks, poll by task ID, and retrieve generated audio URLs from resultJson.resultUrls when the task completes.
Suno Sounds is a text-to-audio workflow for creating sound effects and ambient sounds from natural language descriptions. The ApiPass integration exposes the public model name suno/sounds and supports V5 and V5_5 versions. It is designed for developers building audio tools, game sound pipelines, video editing workflows, creative apps, and background ambience generators. The API accepts a concise prompt up to 500 characters, optional looping, tempo, musical key, and lyric-subtitle extraction settings, then returns results through an asynchronous task workflow.
Generate sound effects from plain English prompts. Describe the source, setting, texture, motion, and mood, then submit the task through /api/v1/jobs/createTask using the fixed public model name suno/sounds.
Create background atmospheres such as rain, ocean waves, room tone, nature beds, sci-fi drones, or game ambience. Use soundLoop when a seamless loop is needed for playback in apps, games, or installations.
A successful create response returns data.taskId. Poll /api/v1/jobs/recordInfo until the state is success or fail. When successful, deserialize data.resultJson and read resultUrls for generated audio links.
Turn text descriptions into sound effects and ambient audio. Prompts can describe sound source, environment, mood, duration feel, rhythm, and texture, with a maximum length of 500 characters.
Choose V5 or V5_5 for generation. If no version is provided, ApiPass defaults to V5. Version matching is case-insensitive and unsupported versions are rejected before billing and upstream processing.
Control whether the generated sound should loop, set soundTempo from 1 to 300 BPM, and select a supported soundKey such as Any, Cm, D#m, F#, A, or B.
Generate footsteps, UI hits, magical loops, sci-fi ambience, creature cues, and environmental beds from short text prompts. Use soundLoop for looping backgrounds and soundTempo for rhythm-sensitive effects.
Create cinematic whooshes, transitions, natural environments, impact sounds, and mood-setting audio for short videos, editing tools, and content creation workflows.
Build ambience generators for rain, ocean waves, quiet rooms, forest beds, or soft drones. The asynchronous workflow lets applications submit tasks and retrieve finished audio URLs when ready.
Use the ApiPass task workflow to submit, monitor, and retrieve generated sound effects reliably.
Use POST /api/v1/jobs/createTask to submit a sound generation request. The response only confirms task submission and returns data.taskId. Use GET /api/v1/jobs/recordInfo with that taskId to monitor waiting, queuing, generating, success, or fail states.
Both V5 and V5_5 are supported by the Suno Sounds API on ApiPass. If input.model is omitted, V5 is used. Values are normalized case-insensitively, while unsupported versions are rejected before billing.
Use the optional channel parameter to control provider routing. auto is the default and lets ApiPass allocate tasks across available providers based on real-time pricing and stability metrics.
starter is ultra-low-cost with limited quotas and weaker stability. regular is a standard option with moderate stability. official uses the model native API with high stability, fast task execution, and official pricing.
ApiPass validates required fields, supported versions, boolean options, soundTempo range, and soundKey values before sending requests upstream. Unsupported versions are rejected before billing and provider execution.
Send a POST request to /api/v1/jobs/createTask with model set to suno/sounds and input.prompt containing your sound description. Optional fields include input.model, input.soundLoop, input.soundTempo, input.soundKey, and input.grabLyrics.
A successful create response returns data.taskId. Store this ID in your application because the create response does not contain finished audio. It only means the asynchronous generation task was submitted.
Poll /api/v1/jobs/recordInfo until the task reaches success or fail. If callBackUrl was provided during task creation, ApiPass will also POST a completion payload with the same structure as the Query Task API response.
When the task succeeds, deserialize data.resultJson first, then read the resultUrls array for generated audio URLs. URLs are usually ApiPass CDN links, but upstream URLs may be returned if CDN storage is unavailable.
The API page shows the parameter schema, but Suno also has several business-specific mode combinations and callback rules that are easy to miss.
All APIs require authentication via Bearer Token.
Authorization: Bearer
Submit a Suno Sounds task to generate a sound effect or ambient sound from a text description.
The API accepts a JSON payload with the following structure:
1{
2 "model": "suno/sounds",
3 "callBackUrl": "string (optional)",
4 "channel": "auto",
5 "input": {
6 "prompt": "string",
7 "model": "V5",
8 "soundLoop": false,
9 "soundTempo": 96,
10 "soundKey": "Any",
11 "grabLyrics": false
12 }
13}modelRequiredstringPublic ApiPass model name. For this API, it must be fixed as suno/sounds.
"suno/sounds"
inputRequiredobjectSounds parameter object. This must be a JSON object.
{"prompt":"Rain falling on a quiet window at night"}callBackUrlOptionalstringCallback URL for task completion notifications. If omitted, no callback will be sent.
"https://your-domain.com/api/callback"
channelOptionalstringOptional APIPASS provider routing mode. The default channel is auto; APIPASS automatically allocates tasks across available providers based on real-time pricing and stability metrics. starter is ultra-low-cost with limited quotas and weaker stability. regular is standard and much cheaper than official APIs with moderate stability. official uses the model native API with high stability, fast task execution, and official pricing.
The default value for the channel parameter is auto. When enabled, APIPASS automatically allocates tasks across available providers based on real-time pricing and stability metrics to balance minimal cost and reliable performance. starter is ultra-low-cost with limited quotas and weaker stability; regular is standard and much cheaper than official APIs with moderate stability; official uses the model native API with high stability, fast task execution, and official pricing.
Available options:
auto
The input object contains the following parameters:
input.promptRequiredstringText description of the sound effect or ambient sound to generate.
Describe the sound source, environment, mood, duration feel, rhythm, and texture for more stable results. The prompt must not exceed 500 characters.
"A short cinematic ocean wave with a soft breeze"
input.modelOptionalstringSuno Sounds version. Defaults to V5 when omitted. Version matching is case-insensitive and normalized before generation.
Only V5 and V5_5 are supported. Aliases model_version, modelVersion, and version are also accepted and normalized to model before the upstream request.
Available options:
"V5"
input.soundLoopOptionalbooleanWhether to generate a sound effect that can loop seamlessly. Default: false.
Compatible aliases sound_loop and loop are also accepted.
false
input.soundTempoOptionalintegerSound tempo in BPM.
Must be an integer from 1 to 300. Numeric strings such as "120" are accepted and normalized to numbers; decimals, booleans, non-numeric values, and out-of-range values are rejected. Compatible aliases sound_tempo and tempo are also accepted.
96
input.soundKeyOptionalstringMusical key for the generated sound. Default: Any.
Compatible aliases sound_key and key are also accepted. If omitted, the adapter follows the upstream default behavior for Any.
Available options:
"Any"
input.grabLyricsOptionalbooleanWhether to ask the upstream provider to additionally extract lyric subtitles after task completion. Default: false.
Sound effect tasks usually keep this set to false. The alias grab_lyrics is also accepted.
false
1curl --request POST \
2 --url "https://api.apipass.dev/api/v1/jobs/createTask" \
3 --header "Authorization: Bearer ${APIPASS_API_KEY}" \
4 --header "Content-Type: application/json" \
5 --data '{
6 "model": "suno/sounds",
7 "callBackUrl": "https://your-domain.com/api/callback",
8 "channel": "auto",
9 "input": {
10 "prompt": "A short cinematic ocean wave with a soft breeze",
11 "model": "V5",
12 "soundLoop": false,
13 "soundTempo": 96,
14 "soundKey": "Any",
15 "grabLyrics": false
16 }
17 }'1{
2 "code": 200,
3 "message": "success",
4 "data": {
5 "taskId": "task_xxxxxxxxxxxxxxxx"
6 }
7}codeStatus code, 200 for success, others for failure.
messageResponse message. When the request fails, this contains the error description.
data.taskIdApiPass task ID used to query task status and retrieve generated audio results.
MiniMax
MiniMax
MiniMax Music 1.5 AI music generation model, supports lyrics and style prompt to generate music
Starting from
0 credits
Starting from
0 credits