Seed Audio 1.0

Seed Audio 1.0 · ByteDance — Text to audio · 4 file formats. Call it through one queue API and pay for the options you pick.

modellane/seed-audio-1.0 · Text to audio · ByteDance

Text to audio model: 4 file formats.

Vendor
ByteDance
Task
Text to audio
Output
Audio
Price
From $0.39 per run

Input parameters

  • Text text — required The text fed into the generation.
  • References references — optional
  • File format format — optional, options: MP3, WAV, PCM, OGG opus The file format of the output.
  • Sample rate sample_rate — optional, default: 24000, options: 8000, 16000, 24000, 32000, 44100, 48000 The sample rate of the audio output; a higher value makes the file larger.
  • Pitch adjustment pitch_rate — optional, default: 0, range: -12–12
  • Speech rate speech_rate — optional, default: 0, range: -50–100
  • Loudness adjustment loudness_rate — optional, default: 0, range: -50–100

Output and retention

The generated file and your input are kept for seven days and then deleted.

Queue API

Submit to the queue: POST /v1/queue/modellane/seed-audio-1.0

Status, result, cancellation and error codes work the same for every model; see the API docs.

Playground

Everything on this page is public; you need an account to run the model.