Vidu Contest
WaveSpeed.ai
text-to-audio

text-to-audio

ElevenLabs Music

elevenlabs/music

ElevenLabs Music generates original songs from text descriptions. Create instrumentals or full compositions with customizable duration. Ready-to-use REST inference API, best performance, no cold starts, affordable pricing.

Input
Generate instrumental music without vocals.

Idle

このリクエストには1回あたりで$0.083の費用がかかります。

$1でおよそ12回実行できます。

サンプルすべて表示

README

ElevenLabs Music

ElevenLabs Music is an AI music generation model that creates songs with vocals or instrumental tracks from text prompts. Describe the genre, mood, and style, include lyrics with structure markers, and the model generates professional-quality music with flexible output formats.

Why Choose This?

  • Songs with vocals or instrumental Generate complete songs with AI vocals, or switch to instrumental-only mode.

  • Flexible song length Control output duration precisely with millisecond-level adjustment.

  • Multiple output formats Export as MP3 (standard/high quality) or WAV at various sample rates.

  • Style and lyrics in one prompt Combine style tags and structured lyrics in a single prompt field.

  • Prompt Enhancer Built-in tool to automatically improve your music descriptions.

Parameters

ParameterRequiredDescription
promptYesStyle description and lyrics with structure markers
music_length_msNoOutput duration in milliseconds (default: 40000)
force_instrumentalNoGenerate instrumental only without vocals (default: disabled)
output_formatNoOutput format (see options below, default: mp3_standard)

Output Format Options

FormatDescription
mp3_standardStandard quality MP3
mp3_high_qualityHigh quality MP3
wav_16khzWAV at 16kHz sample rate
wav_22khzWAV at 22kHz sample rate
wav_24khzWAV at 24kHz sample rate
wav_cd_qualityWAV at CD quality (44.1kHz)

Prompt Format

Combine style tags and lyrics in the prompt field. Start with genre, mood, and instrument descriptions, then add structured lyrics:

Example:

Hard Trap, Hip Hop, 808 bass, energetic flow, confident male rap vocals, brass stabs, hype music, motivational sports anthem. [Verse] Laced up tight, ready to go Putting on a major show Sweat and tears on the floor Coming back to get some more [Chorus] We don't stop, we don't quit Every rep, every hit

How to Use

  1. Write your prompt — describe the musical style and include lyrics with structure markers.
  2. Set duration — adjust music_length_ms for desired song length.
  3. Enable instrumental (optional) — check to generate music without vocals.
  4. Choose output format — select MP3 or WAV at your preferred quality.
  5. Run — submit and download your generated music.

Pricing

DurationCost
Per second$0.0083

Examples

  • 40s song → $0.33
  • 120s song → $1.00
  • 300s (5 min) → $2.49

Best Use Cases

  • Original Music — Generate complete songs for creative projects.
  • Instrumental Tracks — Create background music for videos, podcasts, and games.
  • Rap & Hip Hop — Produce tracks with AI vocals and beat production.
  • Demo Production — Quickly prototype song ideas before studio recording.
  • Content Soundtracks — Custom music for social media and marketing.

Pro Tips

  • Use the Prompt Enhancer to refine your style descriptions.
  • Include specific genre, instrument, and mood tags at the start of your prompt.
  • Use [Verse], [Chorus], [Bridge] markers in lyrics for structured song arrangement.
  • Enable force_instrumental for background music or beat production.
  • Use wav_cd_quality for highest audio fidelity, mp3_standard for smaller file sizes.
  • Adjust music_length_ms to match your desired song duration precisely.

Notes

  • Only prompt is required; other parameters have defaults.
  • Duration is set in milliseconds (e.g., 40000 = 40 seconds, 120000 = 2 minutes).
  • force_instrumental overrides any lyrics in the prompt.
  • For best results, combine detailed style tags with well-structured lyrics.

Related Models