Mirelo AI Sfx 2.0 Text To Audio API Documentation

Mirelo AI Sfx 2.0 Text To Audio API Documentation

Playground

Mirelo SFX 2.0 Text-to-Audio generates sound effects and ambience from text descriptions, with positive and negative prompt controls, configurable duration, and one audio output per request for sound design, video production, games, ads, and creative audio workflows. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Mirelo SFX 2.0 Text-to-Audio generates sound effects and ambience directly from text descriptions. Describe the sound you want, use an optional negative prompt to exclude unwanted elements, choose the duration and audio format, and generate a finished audio track.

It is designed for game audio, cinematic sound design, environmental ambience, Foley-style effects, and other non-speech audio workflows.

Why Choose This?

• Text-to-sound generation
  Create sound effects and ambience directly from natural-language descriptions.

• Positive and negative guidance
  Describe both what should be present and what should be avoided in the generated audio.

• Flexible duration
  Generate audio from 0.1 seconds up to 600 seconds.

• Multiple output formats
  Export as wav, mp3, aac, or flac.

• Bitrate control
  Configure bitrate for MP3 and AAC when specific encoding requirements matter.

• Seed support
  Use a fixed seed when reproducibility is useful.

Parameters

How to Use

1. Describe the sound — Specify the sound source, environment, intensity, texture, and how it should evolve.
2. Add a negative prompt optional — Describe sounds, voices, music, or other elements that should be avoided.
3. Set duration — Choose a length from 0.1 to 600 seconds.
4. Choose output format — Select wav, mp3, aac, or flac.
5. Set bitrate optional — Configure bitrate when using MP3 or AAC.
6. Set seed optional — Use a fixed seed when reproducibility is needed.
7. Submit — Generate the audio and retrieve the result.

Pricing

Pricing is based on the requested duration.

The rate is $0.016 per requested second.

negative_prompt, output_format, audio_bitrate_kbps, and seed do not add separate charges.

Best Use Cases

• Game sound effects — Generate interaction sounds, environmental effects, impacts, machinery, creatures, and other game audio.
• Cinematic sound design — Create dramatic effects, transitions, atmospheres, and environmental sound.
• Ambient soundscapes — Generate rain, city ambience, forests, interiors, crowds, and other background environments.
• Foley-style audio — Create footsteps, object handling, doors, fabric movement, and other action-related sounds.
• Soundtrack prototyping — Explore alternate sound directions before final production.
• Interactive media — Generate custom sound assets for applications, installations, and immersive experiences.

Pro Tips

• Describe concrete sound sources, materials, movement, intensity, and environment.
• Explain how the sound should change over time when progression matters.
• Use negative_prompt to reduce unwanted music, speech, voices, or background elements.
• Start with shorter generations when testing a new sound direction before creating longer audio.
• Use wav or flac when lossless output is preferred.
• Set a fixed seed when comparing prompt or parameter changes.

Notes

• prompt is required and supports up to 2000 characters.
• negative_prompt supports up to 1000 characters.
• duration supports 0.1–600 seconds and defaults to 30.
• output_format defaults to wav.
• Supported output formats are wav, mp3, aac, and flac.
• Leave audio_bitrate_kbps empty for WAV and FLAC.
• MP3 supports 32, 40, 48, 56, 64, 80, 96, 112, 128, 160, 192, 224, 256, or 320 kbps.
• AAC accepts an integer target bitrate from 32 to 256 kbps; actual encoded bitrate may be lower.
• When no bitrate is specified, MP3 uses variable bitrate and AAC uses a 256 kbps target.
• This endpoint is designed for sound effects and ambience rather than text-to-speech or voice cloning.

Related Models

• Mirelo SFX 2.0 Video-to-Audio — Generate synchronized sound effects from video with optional text guidance and speech preservation.
• Mirelo SFX 2.0 Video-to-Video — Add synchronized sound effects to an existing video and return the video with the new soundtrack.

Authentication

For authentication details, please refer to the Authentication Guide.

API Endpoints

Submit Task & Query Result

set -euo pipefail

export WAVESPEED_API_KEY="your-api-key"

REQUEST_BODY=$(cat <<'JSON'
{
  "prompt": "A cinematic ocean wave at sunrise, highly detailed",
  "duration": 30,
  "output_format": "wav"
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/mirelo-ai/sfx-2.0/text-to-audio" \
  -H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
  -H "Content-Type: application/json" \
  -d "${REQUEST_BODY}")

TASK=$(printf '%s' "${SUBMIT_RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "${TASK}" | jq -r '.id // empty')
if [ -z "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"

# 2. Poll until the prediction finishes.
while true; do
  RESPONSE=$(curl --silent --show-error --fail-with-body \
    "${RESULT_URL}" \
    -H "Authorization: Bearer ${WAVESPEED_API_KEY}")
  RESULT=$(printf '%s' "${RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
  STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')

  case "${STATUS}" in
    completed) printf '%s\n' "${RESULT}" | jq '.outputs'; break ;;
    failed|cancelled|timeout|deleted) printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
    *) sleep 2 ;;
  esac
done

Parameters

Task Submission Parameters

Request Parameters

Conditional constraints

• When audio_bitrate_kbps is provided: output_format is required; output_format must be one of mp3, aac.
• When output_format is mp3 and audio_bitrate_kbps is provided: audio_bitrate_kbps must be one of 32, 40, 48, 56, 64, 80, 96, 112, 128, 160, 192, 224, 256, 320.
• When output_format is aac and audio_bitrate_kbps is provided: audio_bitrate_kbps must be at most 256.

Response Parameters

Result Request Parameters

Result Response Parameters