Seed Audio 1.0 Prompted Speech

ByteDance Seed Audio 1.0 turns natural-language prompts into speech and audio with control over format, sample rate, speed, volume and pitch.

  • ByteDance
  • 1 variant
  • $0.0025 per second

Working with Seed Audio.

Seed Audio 1.0 takes a natural-language prompt and produces speech or audio, exposing the parameters an engineer usually wants: output format, sample rate, speed, volume and pitch. That control surface is what distinguishes it from voice-only TTS models.

When to choose Seed Audio

Choose Seed Audio when the technical properties of the audio file matter as much as the voice — a fixed sample rate for a pipeline, a specific pitch or pace. MiniMax Speech is the pick for a latency choice, Google's TTS for inline delivery tags.

Questions about Seed Audio

The short answers. For anything specific to your setup, talk to our team.

Talk to an engineerPlan for your expected volume.
  • Format, sample rate, speed, volume and pitch, set per request rather than fixed by the model.

Ready to close the gap?

Find the model. Build the workflow. Make it production-ready.