ElevenLabs Music v2 APIのcomposition planで曲調と長さを指定して音声データを作成できるようになったので試してみた

export ELEVENLABS_API_KEY="<YOUR_ELEVENLABS_API_KEY>"

jq -n \
  --arg prompt 'Create a 10-second instrumental city pop loop for a product demo. Structure it as a soft intro, a brighter main groove, and a clean ending. Use 95 BPM, electric piano, muted guitar, light bass, tight drums, and no vocals.' \
  '{prompt:$prompt,music_length_ms:10000,model_id:"music_v2"}' \
| curl -sS \
  -X POST 'https://api.elevenlabs.io/v1/music/plan' \
  -H "xi-api-key: ${ELEVENLABS_API_KEY}" \
  -H 'Content-Type: application/json' \
  --data-binary @- \
| jq .

{
  "chunks": [
    {
      "text": "[Soft Intro]",
      "duration_ms": 3000,
      "positive_styles": [
        "city pop",
        "instrumental",
        "95 bpm",
        "electric piano",
        "muted guitar"
      ],
      "negative_styles": [
        "vocals",
        "aggressive",
        "heavy metal"
      ],
      "context_adherence": "high"
    },
    {
      "text": "[Brighter Main Groove]",
      "duration_ms": 4500,
      "positive_styles": [
        "bright funky muted guitar riffing",
        "tight snare drum and hi-hat groove",
        "funky walking bassline"
      ],
      "negative_styles": [
        "distorted lead guitar",
        "vocals"
      ],
      "context_adherence": "high"
    },
    {
      "text": "[Clean Ending]",
      "duration_ms": 3000,
      "positive_styles": [
        "staccato electric piano stabs",
        "clean guitar tail",
        "snare hit ending on beat"
      ],
      "negative_styles": [
        "fade out",
        "reverb crash",
        "vocals"
      ],
      "context_adherence": "high"
    }
  ]
}

jq -n --slurpfile plan /tmp/elevenlabs_music_v2_plan.json '{
  model_id: "music_v2",
  composition_plan: $plan[0]
}' \
| curl -sS \
  -X POST 'https://api.elevenlabs.io/v1/music?output_format=mp3_48000_192' \
  -H "xi-api-key: ${ELEVENLABS_API_KEY}" \
  -H 'Content-Type: application/json' \
  --data-binary @- \
  -o elevenlabs_music_v2_citypop.mp3

Content-Type: audio/mpeg
MPEG Layer III, 192 kbps, 48 kHz, Joint Stereo
Duration: 10.512 seconds

{
  "model_id": "music_v2",
  "composition_plan": {
    "chunks": [
      {
        "text": "[Intro]\n{instrumental hook}",
        "duration_ms": 4000,
        "positive_styles": [
          "modern J-pop",
          "bright female vocal production",
          "128 BPM",
          "A major",
          "sparkling electric piano",
          "clean electric guitar",
          "tight pop drums",
          "warm synth pad",
          "catchy instrumental hook",
          "polished radio mix"
        ],
        "negative_styles": [
          "existing artist imitation",
          "cover song",
          "dark",
          "heavy metal",
          "lo-fi",
          "distorted vocals"
        ],
        "context_adherence": "high"
      },
      {
        "text": "[Verse 1]\n夜明け前のホームで\nほどけた夢を結んだ",
        "duration_ms": 8000,
        "positive_styles": [
          "gentle verse",
          "clear Japanese female vocals",
          "natural Japanese pronunciation",
          "spacious phrasing",
          "soft electric piano",
          "light guitar arpeggios",
          "subtle sidechain synth",
          "steady pop groove"
        ],
        "negative_styles": [
          "rap",
          "shouting",
          "spoken word",
          "a cappella",
          "crammed lyrics",
          "rushed syllables",
          "overly dramatic vibrato"
        ],
        "context_adherence": "high"
      },
      {
        "text": "[Pre-Chorus]\n風が背中を押す",
        "duration_ms": 6000,
        "positive_styles": [
          "rising pre chorus",
          "clear Japanese female vocals",
          "natural Japanese pronunciation",
          "building drums",
          "layered harmonies",
          "uplifting synth lift",
          "snare build",
          "emotional but hopeful"
        ],
        "negative_styles": [
          "dropout",
          "quiet ending",
          "dark chord change",
          "crammed lyrics",
          "rushed syllables",
          "screaming"
        ],
        "context_adherence": "high"
      },
      {
        "text": "[Chorus]\n走れ 朝焼けライン\n胸の奥まで照らして\n新しい今日へ",
        "duration_ms": 11000,
        "positive_styles": [
          "big J-pop chorus",
          "clear Japanese female vocals",
          "natural Japanese pronunciation",
          "spacious singable topline",
          "catchy topline",
          "full band",
          "bright synth strings",
          "driving drums",
          "wide vocal harmonies",
          "uplifting melody",
          "radio-ready hook"
        ],
        "negative_styles": [
          "sad ballad",
          "minimal arrangement",
          "low energy",
          "crammed lyrics",
          "rushed syllables",
          "spoken voice"
        ],
        "context_adherence": "high"
      },
      {
        "text": "[Outro]\n{short instrumental tag}\n朝焼けライン",
        "duration_ms": 3000,
        "positive_styles": [
          "short outro",
          "clean final chord",
          "sparkling synth tail",
          "memorable pop ending"
        ],
        "negative_styles": [
          "long fade out",
          "abrupt cut",
          "dark ending"
        ],
        "context_adherence": "high"
      }
    ]
  }
}

curl -sS \
  -X POST 'https://api.elevenlabs.io/v1/music?output_format=mp3_48000_192' \
  -H "xi-api-key: ${ELEVENLABS_API_KEY}" \
  -H 'Content-Type: application/json' \
  --data-binary @composition-plan.json \
  -o elevenlabs_jpop_asayake-line.mp3

HTTP 200
Content-Type: audio/mpeg
File size: 769,005 bytes
Format: MP3, 48 kHz, 192 kbps
Duration: 32.040 seconds

{
  "model_id": "music_v2",
  "composition_plan": {
    "chunks": [
      {
        "text": "[Main Theme - immediate start]\n{full heroic orchestral theme begins on the first beat}",
        "duration_ms": 12000,
        "positive_styles": [
          "original fantasy RPG orchestral music",
          "immediate main theme",
          "no intro",
          "grand symphonic arrangement",
          "full strings",
          "heroic brass fanfare",
          "timpani and cymbal swells",
          "cinematic game soundtrack",
          "majestic and adventurous",
          "140 BPM"
        ],
        "negative_styles": [
          "existing game franchise imitation",
          "cover song",
          "recognizable melody",
          "slow intro",
          "fade in",
          "lyrics"
        ],
        "context_adherence": "high"
      },
      {
        "text": "[Rising Adventure]\n{strings drive forward while brass answers the main theme}",
        "duration_ms": 10000,
        "positive_styles": [
          "driving ostinato strings",
          "French horns answer melody",
          "snare and timpani rhythm",
          "heroic journey feeling",
          "fantasy world map energy"
        ],
        "context_adherence": "high"
      },
      {
        "text": "[Heroic Lift]\n{main theme modulates upward with brighter brass and soaring strings}",
        "duration_ms": 10000,
        "positive_styles": [
          "soaring violin melody",
          "bright brass counter melody",
          "wordless choir texture",
          "uplifting modulation",
          "large fantasy battle theme"
        ],
        "context_adherence": "high"
      },
      {
        "text": "[Climax]\n{full orchestra peaks with percussion hits and triumphant cadence}",
        "duration_ms": 10000,
        "positive_styles": [
          "full orchestra climax",
          "triumphant brass",
          "rapid string runs",
          "crash cymbals",
          "timpani rolls"
        ],
        "context_adherence": "high"
      },
      {
        "text": "[Final Hit]\n{short decisive orchestral ending with a resonant final chord}",
        "duration_ms": 3000,
        "positive_styles": [
          "decisive final chord",
          "orchestral hit",
          "short reverb tail",
          "complete ending",
          "no fade out"
        ],
        "context_adherence": "high"
      }
    ]
  }
}

curl -sS \
  -X POST 'https://api.elevenlabs.io/v1/music?output_format=mp3_48000_192' \
  -H "xi-api-key: ${ELEVENLABS_API_KEY}" \
  -H 'Content-Type: application/json' \
  --data-binary @fantasy-rpg-plan.json \
  -o elevenlabs_fantasy-rpg_45s_no-intro.mp3

HTTP 200
Content-Type: audio/mpeg
File size: 1,080,621 bytes
Format: MP3, 48 kHz, 192 kbps
Duration: 45.024 seconds

{
  "status": "needs_authorization",
  "message": "Neither authorization header nor xi-api-key received, please provide one."
}