Realtime TTS-2 API Pricing
replicate/inworld/realtime-tts-2- Price
- $25.00 per 1M characters
As of November 21, 2026, Realtime TTS-2 costs $25.00 per 1M characters on Replicate.
Realtime TTS-2 pricing by provider
1 listing across 1 provider. Token prices are in US dollars per 1M tokens. The highlighted row is the price quoted above.
| Provider | Model name in LiteLLM | Per 1M chars | Context |
|---|---|---|---|
| Replicate | replicate/inworld/realtime-tts-2 | $25.00 | – |
What Realtime TTS-2 costs in practice
Narrating 500,000 characters
| Replicate | $12.50 |
Use Realtime TTS-2 with LiteLLM
Call Realtime TTS-2 through the LiteLLM Python SDK, or put it behind the LiteLLM proxy and send OpenAI-format requests to /v1/audio/speech. LiteLLM tracks the cost of every request at these prices.
from litellm import speech
response = speech(
model="replicate/inworld/realtime-tts-2",
input="Hello from LiteLLM",
voice="alloy",
)model_list:
- model_name: realtime-tts-2
litellm_params:
model: replicate/inworld/realtime-tts-2
# credentials: see the provider's LiteLLM docs pagecurl http://0.0.0.0:4000/v1/audio/speech \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $LITELLM_API_KEY" \
-d '{
"model": "realtime-tts-2",
"input": "Hello from LiteLLM",
"voice": "alloy"
}'Realtime TTS-2 FAQ
How much does Realtime TTS-2 cost?
Realtime TTS-2 costs $25.00 per 1M characters on Replicate.
Which providers offer Realtime TTS-2?
Realtime TTS-2 is available from Replicate through LiteLLM, using the model name replicate/inworld/realtime-tts-2.
How do I call Realtime TTS-2 with an OpenAI-compatible API?
Use the LiteLLM Python SDK with model="replicate/inworld/realtime-tts-2", or add the model to the LiteLLM proxy's config.yaml and send requests to /v1/audio/speech from any OpenAI client. LiteLLM tracks the cost of every request at the prices on this page.
When did LiteLLM add Realtime TTS-2?
Realtime TTS-2 was added to LiteLLM's model price file on November 11, 2026.
Sources
Prices come from LiteLLM's open-source model_prices_and_context_window.json, which LiteLLM uses to calculate the cost of every request. Maintainers update it from each provider's published pricing, and this page is usually rebuilt within 20 minutes of every change. Provider pricing pages:
LiteLLM docs: Replicate.
Provider pages: Replicate.