{
  "listings": [
    {
      "slug": "elevenlabs-music",
      "name": "ElevenLabs Music API",
      "company": "Eleven Labs Inc.",
      "grade": "BB",
      "fit": "caveat",
      "why": "Sections carry lyric lines and durations up to 600,000 ms, and a copyright refusal returns bad_prompt with a prompt suggestion. The call is synchronous with no job id or idempotency key, and acc-07 found non-English vocals patchy.",
      "source": "https://elevenlabs.io/docs/api-reference/music/compose.md",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/elevenlabs-music"
    },
    {
      "slug": "fal-music",
      "name": "fal music models",
      "company": "Features \u0026 Labels, Inc.",
      "grade": "BB",
      "fit": "caveat",
      "why": "Mureka 9.5 sings up to 5,000 characters of lyrics with a target duration and returns timed lyric sections; the queue returns an id first, and errors are typed, with optional content-policy categories. Language fidelity and the 5-minute bar aren't stated, and no idempotency key exists.",
      "source": "https://api.fal.ai/v1/models?endpoint_id=mureka/v9.5/generate/song\u0026expand=openapi-3.0",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/fal-music"
    },
    {
      "slug": "google-lyria",
      "name": "Google Lyria",
      "company": "Google LLC",
      "grade": "D",
      "fit": "caveat",
      "why": "Lyria 3.5 sings supplied lyrics with section tags in the prompt's language and returns lyrics with the audio. Refusals arrive without a category (acc-15), a timeout can bill a song with no id (acc-28), one SDK path fails (acc-19), and charges show hours later (acc-10).",
      "source": "https://aistudio.google.com/docs/music-generation.md",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/google-lyria"
    },
    {
      "slug": "loudly",
      "name": "Loudly Music API",
      "company": "Loudly GmbH",
      "grade": "F",
      "fit": "caveat",
      "why": "POST /api/ai/manta/songs takes lyrics, gender and instrumental=false, but needs Loudly to switch on manta_access (403 otherwise), has no length field, and states no refusal or language behaviour.",
      "source": "https://b2b-soundtracks-swagger-prd.loudly.com/swagger/b2b_swagger.yaml",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/loudly"
    },
    {
      "slug": "musicgpt",
      "name": "MusicGPT API",
      "company": "MusicGPT Ltd",
      "grade": "D",
      "fit": "caveat",
      "why": "Lyrics, model choice and lyric timestamps go in; a task id and per-request is_flagged with a reason string come back. No maximum length or language support is stated, and no idempotency key exists, so a blind retry may bill again.",
      "source": "https://docs.musicgpt.com/api-documentation/openapi.json",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/musicgpt"
    },
    {
      "slug": "soundverse",
      "name": "Soundverse API",
      "company": "Soundverse Inc.",
      "grade": "E",
      "fit": "caveat",
      "why": "generate_song takes up to 3,000 characters of lyrics with gender or a saved voice, returns a job id at once and takes an Idempotency-Key. Song length isn't a parameter or published, and content refusals have no named error type, only a failed status with error_message.",
      "source": "https://platform.soundverse.ai/docs/song-generation",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/soundverse"
    },
    {
      "slug": "suno-mcp",
      "name": "Suno MCP",
      "company": "Suno, Inc. (United States, terms governed by Massachusetts law)",
      "grade": "F",
      "fit": "caveat",
      "why": "The server turns ideas and lyrics into songs saved to the library, but tool schemas, refusal behaviour and job handling are unpublished, and acc-23 had to stop for a human when only library ids came back.",
      "source": "https://help.suno.com/en/articles/14551361",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/suno-mcp"
    },
    {
      "slug": "beatoven",
      "name": "Beatoven.ai API",
      "company": "Beatoven Private Limited (with subsidiary Beatoven Inc.)",
      "grade": "F",
      "fit": "no",
      "why": "The spec has one prompt field and no lyrics or vocal option; output is an instrumental with bass, chords, melody and percussion stems.",
      "source": "https://github.com/Beatoven/public-api/blob/main/docs/api-spec.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/beatoven"
    },
    {
      "slug": "mubert",
      "name": "Mubert API",
      "company": "Mubert Inc.",
      "grade": "F",
      "fit": "no",
      "why": "Generation takes prompts, images or playlists with no lyrics input; acc-34 found its Mubert adapter can't sing.",
      "source": "https://github.com/MubertAI/skills/blob/main/mubert-generate/SKILL.md",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/mubert"
    },
    {
      "slug": "replicate-musicgen",
      "name": "MusicGen on Replicate",
      "company": "Replicate, LLC",
      "grade": "B",
      "fit": "no",
      "why": "The inputs are a text prompt and an optional melody clip; there's no lyrics input or vocal output.",
      "source": "https://replicate.com/meta/musicgen/llms.txt",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/replicate-musicgen"
    },
    {
      "slug": "soundraw",
      "name": "SOUNDRAW API",
      "company": "SOUNDRAW Inc.",
      "grade": "F",
      "fit": "no",
      "why": "Instrumental background music only; the compose parameters have no lyrics or vocals.",
      "source": "https://soundraw.io/blog/post/add-copyright-free-music-react-app-ai-music-api",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/soundraw"
    },
    {
      "slug": "stable-audio",
      "name": "Stable Audio API",
      "company": "Stability AI Ltd (UK, EU, Switzerland) and Stability AI US Services Corporation (elsewhere)",
      "grade": "F",
      "fit": "no",
      "why": "No lyrics or vocal parameter on any audio route; acc-34 found its Stable Audio adapter can't sing.",
      "source": "https://api.stability.ai/v2alpha/openapi",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/stable-audio"
    }
  ],
  "marks": "yes: the docs show it does the job as the success test says. caveat: it does the job with a limit an agent should know. no: it doesn't do this job. unchecked: we couldn't read it.",
  "meta": {
    "attribution": "Anchor Terminal (https://www.anchorterminal.com)",
    "attributionRequired": true,
    "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)",
    "docs": "https://www.anchorterminal.com/docs/",
    "generatedAt": "2026-11-16",
    "license": "CC-BY-4.0",
    "method": "https://www.anchorterminal.com/benchmark/",
    "methodology": "0.8",
    "openapi": "https://www.anchorterminal.com/openapi.json",
    "preview": false,
    "run": "2026-10-01",
    "runLabel": "October 2026 research run",
    "terms": "https://www.anchorterminal.com/terms/#data"
  },
  "useCase": {
    "accounts": 12,
    "after": [
      "file-storage.upload-file",
      "social-media.publish-post"
    ],
    "area": "content",
    "asks": [
      "make a song about this",
      "turn these lyrics into a song",
      "a personalised birthday song",
      "a 2-minute song about my coding session"
    ],
    "before": [
      "inference.chat-completion"
    ],
    "blockers": [
      "HTTP 200 with PROHIBITED_CONTENT and no category, so the agent can't tell what to change (acc-15)",
      "a synchronous call that bills a song it can't return after a timeout (acc-28)",
      "no Suno API outside the MCP server, and the unofficial web route breaks on captchas and encrypted downloads (acc-13, acc-20, acc-21)",
      "the same model fails through one SDK path and works through another (acc-19)",
      "charges show hours after the call, so a retry loop overspends unseen (acc-10)"
    ],
    "capabilities": [
      "audio.music",
      "audio.vocals",
      "audio.composition-plan"
    ],
    "category": "music-generation",
    "categoryName": "Music generation",
    "checked": "2026-11-15",
    "companies": {
      "fit": 0,
      "fitWithLimit": 7,
      "tagged": 16
    },
    "competition": "none",
    "fits": null,
    "fitsWithLimit": [
      "elevenlabs-music",
      "fal-music",
      "google-lyria",
      "loudly",
      "musicgpt",
      "soundverse",
      "suno-mcp"
    ],
    "id": "music-generation.full-song-vocals",
    "listings": {
      "caveat": 7,
      "no": 5,
      "notRead": 0,
      "tagged": 16,
      "unchecked": 0,
      "yes": 0
    },
    "name": "Write and sing a complete song from a prompt or lyrics",
    "status": "draft",
    "success": "A song of at least 90 seconds sung from the supplied lyrics and sections in the requested language, returned as a playable file, or a refusal that names its reason, from one job. Measured: the sung lyrics match the supplied text and sections, and the job finishes within 5 minutes.",
    "url": "https://www.anchorterminal.com/api/v1/use-cases/music-generation.full-song-vocals.json",
    "weight": 27,
    "weightBasis": "12 of 43 links, the largest group: Lyria, ElevenLabs and Suno song attempts on HN, the Google AI forum and GitHub, of which 7 are failure reports (refusals, lost billed jobs, SDK errors, the unofficial Suno route breaking)"
  }
}
