# Mureka | Generate Lyrics Mureka Generate Lyrics is a text generation model that creates original song lyrics from minimal or no prior content. ## API Information - **Model Slug:** mureka-generate-lyrics - **Branded URL:** https://www.eachlabs.ai/mureka/mureka/mureka-generate-lyrics - **Provider:** Mureka - **Category:** Text to Text - **Output Type:** object - **Status:** active - **Base Cost:** $0.009 per execution - **Estimated Processing Time:** 5 seconds - **Interactive Demo:** https://www.eachlabs.ai/ai-models/mureka-generate-lyrics ## Pricing - **Charge Type:** dynamic - **Estimate:** $0.009 per execution - **Pricing Details:** default: $0.009 ## Input Schema | Parameter | Type | Required | Default | Constraints | Description | |-----------|------|----------|---------|-------------|-------------| | prompt | string | Yes | - | - | Describe the song you want to generate. Include details like theme, mood, genre, story, or specific ideas. The more context you provide, the better the generated lyrics will match your vision. | ## Example Request ```bash curl -X POST https://api.eachlabs.ai/v1/prediction/ \ -H "Authorization: Bearer YOUR_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "mureka-generate-lyrics", "input": { "prompt": "Slow, emotional winter song about falling snow." } }' ``` ## Output Schema Response returned by `GET /v1/prediction/{id}` when the job completes: ```json { "status": "success", "predictionID": "string", "output": "object", "metrics": { "predict_time": "number (seconds)" } } ``` ## Polling ```bash curl https://api.eachlabs.ai/v1/prediction/{PREDICTION_ID} \ -H "Authorization: Bearer YOUR_API_KEY" ``` | Status | Meaning | |--------|---------| | `processing` | Still running — poll again | | `success` | Done — read `output` | | `error` | Failed — read `message` / `details` | ## Webhook (alternative to polling) Pass `"webhook_url": "https://your.host/path"` in the create request. Eachlabs POSTs this payload when the job ends: ```json { "exec_id": "prediction-uuid", "status": "succeeded", "output": "https://...", "error": "" } ``` `status` is `"succeeded"` or `"failed"`. `exec_id` equals the `predictionID` from create. Return 2xx within 30 seconds. ## Errors Error body: `{ "status": "error", "message": "...", "details": "..." }` | Code | Meaning | |------|---------| | `400` | Invalid input | | `401` | Missing / invalid `Authorization` bearer token | | `404` | Unknown model or prediction id | | `429` | Rate limit — 100 creates / min, 10 concurrent per key | | `5xx` | Retry with backoff | ## Overview **mureka-generate-lyrics — Text-to-Text AI Model** Developed by Mureka as part of the mureka family, **mureka-generate-lyrics** is a specialized text-to-text AI model that generates original song lyrics from simple prompts or no input at all, solving the challenge of writer's block for musicians and content creators. This integrated lyrics generator within Mureka's AI music platform crafts coherent, genre-specific verses, choruses, and bridges, enabling rapid ideation for complete song compositions. Whether you're searching for an "AI lyrics generator" or "generate song lyrics from prompt," **mureka-generate-lyrics** stands out by leveraging advanced musical reasoning to produce structured lyrics that align with specified moods, languages, and themes, ready for pairing with Mureka's melody and vocal synthesis tools. ## Usage Notes - API Base URL: `https://api.eachlabs.ai/v1` - Authentication: send `Authorization: Bearer YOUR_API_KEY`. Generate a key from the Eachlabs dashboard at https://www.eachlabs.ai/dashboard/api-keys. - File-typed parameters (`*_url`, `image_url`, `video_url`, `audio_url`, etc.) accept publicly-reachable HTTPS URLs only. Upload your asset first (GCS / S3 / your CDN) and pass the resulting URL. Data-URIs and localhost URLs are rejected. - For structured parameters (arrays / objects) send real JSON values, not stringified payloads. - Monetary values are reported in USD; per-token / per-megapixel rates may be billed in micro-cents internally. - Prefer `webhook_url` over polling for long-running predictions — see the Webhook Callback section.