vaaya / catalog / seed-speech v2

Seed-Speech v2 for AI agents

ByteDance's speech model for expressive text-to-speech voices at a low per-character price. Called through Vaaya, billed per call — no ByteDance account.

~4¢ / 1,000 chars

Model by ByteDance. Called through Vaaya — no ByteDance account or API key.

What it's for

Expressive text-to-speech voices at a low per-character price.

Built by ByteDance. Runs on your Vaaya balance — no ByteDance account or API key.

Request it by name, or describe the audio and Vaaya routes to a fitting model.

Returns an audio URL.

How to ask your agent

Connect Vaaya, then just say it in plain language. For example:

❯Use Vaaya to read this announcement aloud in an upbeat voice.

❯Use Vaaya to run this on Seed-Speech v2.

What you get back

{
  "audio": { "url": "https://…/output.mp3" },
  "model": "seed-speech--tts--v2"
}

Pricing

~4¢ per 1,000 characters of script. Charges are shown in cents and recorded in your transaction history. Set a maximum cost for each call. Failed calls are not charged.

Try it with your agent.

Connect Vaaya and describe what you want to do. Your agent can find a suitable service and call it within your budget.

npx @vaaya/mcp install