Create README.md

README.md

@@ -0,0 +1,135 @@
+---
+language:
+  - en
+license: other
+pipeline_tag: text-to-audio
+tags:
+  - suno
+  - text-to-audio
+  - music-generation
+inference: false
+---
+
+# Suno API
+
+**Model Page:** [Suno API](https://apiframe.ai/models/suno)
+
+Community model card for calling Suno through a REST API.
+
+Suno has no official public API. This repo documents the `suno` model as exposed by Apiframe: text-to-music on the current V4–V5.5 line, two tracks per job, custom or auto lyrics, and follow-up actions (extend, cover, add vocals, stems).
+
+This repository does not host weights. Suno is a closed model. Inference runs remotely.
+
+<img src="https://apiframe.ai/models-examples/suno-cover-finish-line.webp" alt="Sample output" width="280" />
+
+## Model description
+
+| | |
+|---|---|
+| Architecture | Suno (default `V4_5PLUS`; pin `V4`, `V4_5`, `V5`, or `V5_5`) |
+| Task | text-to-music; lyrics-to-music |
+| Output | 2 tracks (`audioUrl`, `imageUrl`, `title`, `duration`) |
+| Typical latency | ~110s |
+
+## How to use
+
+```bash
+pip install requests
+```
+
+```python
+import os
+import time
+import requests
+
+API = "https://api.apiframe.ai/v2"
+headers = {
+    "X-API-Key": os.environ["APIFRAME_API_KEY"],
+    "Content-Type": "application/json",
+}
+
+job = requests.post(
+    f"{API}/music/generate",
+    headers=headers,
+    json={
+        "model": "suno",
+        "prompt": "upbeat electronic track with synth arpeggios and driving bass",
+        "sunoParams": {
+            "model_version": "V4_5PLUS",
+            "style": "electronic, synthwave",
+        },
+    },
+).json()
+
+while True:
+    result = requests.get(f"{API}/jobs/{job['jobId']}", headers=headers).json()
+    if result["status"] in ("COMPLETED", "FAILED"):
+        break
+    time.sleep(2)
+
+print(result.get("result"))
+```
+
+`result["tracks"]` is a list of 2 songs. Pass `webhookUrl` on the generate call if you do not want to poll.
+
+With `custom_mode: false` (default), `prompt` is a description (max 500 characters). With `custom_mode: true`, `prompt` is lyrics (max 5,000 characters). Set `auto_lyrics: true` to keep a long prompt as a description and let Suno write the lyrics.
+
+### Custom lyrics
+
+```python
+import os
+import requests
+
+headers = {
+    "X-API-Key": os.environ["APIFRAME_API_KEY"],
+    "Content-Type": "application/json",
+}
+
+requests.post(
+    "https://api.apiframe.ai/v2/music/generate",
+    headers=headers,
+    json={
+        "model": "suno",
+        "prompt": "[Verse 1]\nWalking through the city lights\nNeon glow on rainy nights\n\n[Chorus]\nWe are the dreamers, we are the stars",
+        "sunoParams": {
+            "custom_mode": True,
+            "title": "City Dreamers",
+            "style": "pop, indie",
+            "vocal_gender": "f",
+        },
+    },
+)
+```
+
+### Follow-up actions
+
+```python
+import os
+import requests
+
+headers = {
+    "X-API-Key": os.environ["APIFRAME_API_KEY"],
+    "Content-Type": "application/json",
+}
+
+requests.post(
+    "https://api.apiframe.ai/v2/music/suno/action",
+    headers=headers,
+    json={
+        "parentJobId": "JOB_ID",
+        "action": "extend",  # cover | add_vocals | stems
+        "index": 1,          # 1-2
+    },
+)
+```
+
+## Limitations
+
+- Closed model. No weights, fine-tuning, or local inference.
+- Not an official Suno endpoint. Requires an Apiframe API key (`X-API-Key`).
+- Commercial use follows Suno's terms.
+- Generated media is retained on the CDN for 90 days.
+
+## License
+
+Outputs are subject to Suno's terms. This card is documentation only. Apiframe is not affiliated with, endorsed by, or sponsored by Suno, Inc.