[ inworld-ai ]

realtime-tts-2

Billed at a published markup over the upstream list price. Priced in USD per 1M characters, paid in USDF, with no subscription and no minimum.

← All models
realtime-tts-2·Unavailable·speech·Max input: 2,000 characters

No route to this model is enabled right now. Requests for it are refused with the error code model_unavailable before any balance is held, so nothing is charged. The listed prices apply once a route is enabled.

Input

$43.75

USD per 1M characters

Max input

2,000

characters

Model ID
realtime-tts-2
Modality
speech
Unit
USD per 1M characters
Status
Unavailable
Last verified
—
Endpoints
/v1/audio/speech
Max input
2,000 characters
Pricing basis
Markup
Cache write (5 min)
—
Cache write (1 h)
—
Routes enabled
1 of 1
Price sheet
2026-10-09.1

Routes

ProviderEnabledUpstream input
deepinfraYes$35.00USD per 1M characters

Make your first request

Responses include a receipt with the exact cost.

No account: send the same request to /x402/v1/audio/speech without credentials and the gateway answers 402 with the quote. Pay per request.

This model has no enabled route right now, so the request below is refused with model_unavailable until a route is enabled. Nothing is charged for a refused request.

curl https://api.usdf.fi/v1/audio/speech \
  -H "Authorization: Bearer $FOUNDRY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "realtime-tts-2", "input": "Hello", "response_format": "mp3"}' \
  --output speech.mp3  # the response body is audio bytes