inworld-ai/realtime-tts-2

deepinfra/inworld-ai/realtime-tts-2

audioContext —

Realtime TTS 2.0 is a low-latency text-to-speech model with natural language steering, allowing you to control tone and emotion directly in the prompt (e.g., “[be happy and upbeat] Hello!”). It supports cross-lingual voices and multiple languages, enabling the same voice to speak consistently across different languages. This is an early access preview ahead of full launch, with ongoing improvements to voice quality and steering.

Price

Price$35

per character

Compare this model

Providers

Each row is one seller. Prices are the published rate from that source. A dash means that source did not publish the amount. Sorted by a 3:1 blend of input and output.

Provider	Tag	Quant	Input	Output	Context	Uptime	Status	Source
DeepInfra	—	—	Not published—	Not published—	—	—	Listed	deepinfra

Monthly bill

Token models use the token counts. Image, video, and audio models use units times the flat rate.

Input tokens Output tokens Units

No published price at list price for this workload

Every rate

Unit	Input	Output	Flat	Confidence
character	$35/character	Not published—	Not published—	official

Price history

inworld-ai/realtime-tts-2

input or flat output

Daily snapshots

UTC date	Unit	Input	Output	Flat
2026-10-08	character	$35	Not published—	Not published—
2026-10-09	character	$35	Not published—	Not published—
2026-10-10	character	$35	Not published—	Not published—
2026-10-11	character	$35	Not published—	Not published—
2026-10-12	character	$35	Not published—	Not published—
2026-10-13	character	$35	Not published—	Not published—
2026-10-14	character	$35	Not published—	Not published—
2026-10-15	character	$35	Not published—	Not published—
2026-10-16	character	$35	Not published—	Not published—
2026-10-17	character	$35	Not published—	Not published—
2026-10-18	character	$35	Not published—	Not published—
2026-10-19	character	$35	Not published—	Not published—
2026-10-20	character	$35	Not published—	Not published—
2026-10-21	character	$35	Not published—	Not published—
2026-10-22	character	$35	Not published—	Not published—
2026-10-23	character	$35	Not published—	Not published—
2026-10-24	character	$35	Not published—	Not published—
2026-10-25	character	$35	Not published—	Not published—
2026-10-26	character	$35	Not published—	Not published—
2026-10-27	character	$35	Not published—	Not published—
2026-10-28	character	$35	Not published—	Not published—
2026-10-29	character	$35	Not published—	Not published—
2026-10-30	character	$35	Not published—	Not published—

Alternatives

inworld-ai/realtime-tts-1.5-mini$25/character · Compare
bosonai/HiggsAudioV2.5$20/character · Compare
inworld-ai/realtime-tts-1.5-max$50/character · Compare
Qwen/Qwen3-TTS$20/character · Compare
Qwen/Qwen3-TTS-VoiceDesign$20/character · Compare
Orpheus 3B 0.1 FT$15/1M · Compare

Parameters (1)

tts

Call this model

OpenRouter id deepinfra/inworld-ai/realtime-tts-2. InferenceList does not send the request.

curl

curl https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"deepinfra/inworld-ai/realtime-tts-2","messages":[{"role":"user","content":"Hello"}]}'

JavaScript

await fetch("https://openrouter.ai/api/v1/chat/completions", {
  method: "POST",
  headers: {
    Authorization: "Bearer " + process.env.OPENROUTER_API_KEY,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "deepinfra/inworld-ai/realtime-tts-2",
    messages: [{ role: "user", content: "Hello" }],
  }),
});

Python

import os, json, urllib.request
req = urllib.request.Request(
    "https://openrouter.ai/api/v1/chat/completions",
    data=json.dumps({"model": "deepinfra/inworld-ai/realtime-tts-2", "messages": [{"role": "user", "content": "Hello"}]}).encode(),
    headers={"Authorization": "Bearer " + os.environ["OPENROUTER_API_KEY"], "Content-Type": "application/json"},
)
print(urllib.request.urlopen(req).read().decode())

JSON · History JSON