Independent Audio Analysis API
Every SoundStat feature is computed by us, directly from the audio — not sourced from Spotify or any third party. That isn't just a technical detail: it changes what you're legally allowed to do with the results.
Spotify's Developer Terms restrict using their audio features to train models, build competing products, or resell and monetize the data — whoever passes them on can't charge for them, and whoever uses them can't monetize them. Because SoundStat's analysis is ours, none of those restrictions apply to you.
Ship it in paid products and services.
Pass the analysis on to your own customers.
Use it as features or training data.
Independent & maintained — no deprecation.
| SoundStat | Spotify Audio Features | |
|---|---|---|
| Source | Our own direct analysis | Spotify (endpoint deprecated Nov 2024) |
| Commercial use | ✓ Allowed | ✗ Restricted |
| Resell / redistribute | ✓ Allowed | ✗ Prohibited |
| Train ML models | ✓ Allowed | ✗ Prohibited |
| Availability | ✓ Live & maintained | ✗ Endpoint removed |
Comparison reflects Spotify's publicly documented Developer Terms and the November 2024 deprecation of its audio-features / audio-analysis endpoints. SoundStat is an independent service and is not affiliated with Spotify.
Our system performs detailed audio analysis on each track, extracting comprehensive musical characteristics and building intelligent recommendations. The database grows continuously as we process new tracks.
Previously analyzed tracks are available instantly through our API, with no processing delay
First-time requests trigger our advanced audio analysis system, adding new tracks to the database
Every track includes detailed audio characteristics and recommendation data
{
"id": "0ROMalDdNg3L2HoZP4qFyJ",
"name": "The Four Seasons: Concerto No. 4 in F Minor, RV 297",
"artists": [
"Antonio Vivaldi",
"Adrian Chandler",
"La Serenissima"
],
"popularity": 62,
"genre": "classical",
"isrc": "GBAYE9300142",
"duration_ms": 201853,
"audio_analysis": {
"tempo": {
"value": 172.27
},
"key": {
"value": 7
},
"mode": {
"value": 0
},
"key_confidence": {
"value": 0.53
},
"energy": {
"value": 0.32
},
"danceability": {
"value": 0.49
},
"valence": {
"value": 0.48
},
"instrumentalness": {
"value": 0.73
},
"acousticness": {
"value": 0.97
},
"liveness": {
"value": 0.11
},
"speechiness": {
"value": 0.04
},
"loudness": {
"value": 0.21
},
"segments": {
"count": 82,
"average_duration": 0.35
},
"beats": {
"count": 82,
"regularity": 0.93
}
}
}
Free recommendation system access included with registration
Precise beats per minute detection with typical range 20-250 BPM. Essential for tempo-matching and DJ applications.
Measures consistency of beat patterns. Values from 0.0 to 1.0, where higher values (0.8-1.0) indicate very regular beats.
Detailed breakdown of musical segments including count and average duration. Useful for understanding song structure.
Determines musical key (C, C#, etc.) and mode (major/minor) with confidence scoring. Essential for harmonic mixing.
Measures perceived energy from 0.0 to 1.0, combining volume, timbre, onset rate, and general entropy.
Predicts presence of vocals. 0.0 indicates vocal content, while 1.0 suggests purely instrumental track.
Measures presence of acoustic vs electronic elements. Higher values indicate more acoustic instruments.
Analysis of overall loudness and dynamic range, normalized across the composition.
Combines tempo, rhythm stability, beat strength, and regularity for dance suitability scoring.
Detects the presence of an audience — reverberation, crowd and room ambience. Higher values indicate a live recording.
Detects spoken words. Higher values indicate more speech-like content (rap, spoken word) versus purely musical tracks.
Musical positiveness measurement from 0.0 (sad) to 1.0 (happy). Considers key, mode, and timbre.
Analysis of energy distribution across frequency ranges. Useful for understanding timbral characteristics.
Measures prominence and impact of beats throughout the track. Important for energy assessment.
Choose a subscription plan for predictable monthly costs and lower per-track rates. Unused tracks reset at the end of each billing period.
No subscription needed — pricing automatically adjusts based on your monthly usage. The more tracks you analyze, the bigger discount you receive. The recommendation system is free for all users.
You are only charged for unique track analysis requests within a 30-day period. If you request analysis for the same track multiple times within 30 days, you'll be charged only once. All subsequent requests for previously analyzed tracks are free.
If you analyze the same track on Monday and then again on Friday, you'll only be charged once. The charge for the first analysis will cover all subsequent requests for this track within the next 30 days. This applies to all tracks in your usage, making the service more cost-effective for applications that frequently request the same tracks.
Yes. Spotify deprecated its audio-features and audio-analysis endpoints in November 2024. SoundStat provides equivalent features from its own independent analysis, with a stable, maintained API.
Yes. Because the analysis is SoundStat's own, there are no Spotify-style restrictions — commercial use, resale, redistribution and ML training are all permitted. See our Terms.
Tempo (BPM), key and mode, energy, danceability, valence, acousticness, instrumentalness, liveness, speechiness, loudness, plus beat regularity and segment/structure analysis.
Pay-per-use from $0.01 down to $0.005 per track by monthly volume, or monthly subscriptions ($15 / $49 / $149). You are charged once per unique track per 30 days; repeat lookups are free.
Major milestone: Successfully analyzed over 10,000,000 tracks with our audio analysis system.
Updated and optimized our track analysis algorithm for improved accuracy and performance.
Major milestone: Successfully analyzed over 5,700,000 tracks with our audio analysis system.
Major milestone: Successfully analyzed over 3,000,000 tracks with our audio analysis system.
Published article: Music Recommendations - A Detailed Overview of SoundStat API Extensions.
Major milestone: Successfully analyzed over 1,000,000 tracks with our audio analysis system.
Published article: Understanding Audio Analysis - Learn about different audio analysis systems and how to convert between scales.
SoundStat launches its service
API system and recommendation system development completed.
Fixed critical system bugs. Started development of the API implementation.
Infrastructure scaling preparation completed. Testing and debugging successfully finished.
Initial infrastructure deployment and testing phase completed.
Analysis algorithms optimization for faster processing.
Started development of scalable audio analysis infrastructure.
SoundStat.info start development to provide alternative solution.
Spotify restricts audio features and recommendations API endpoints.