Inworld Realtime TTS-2 — text-to-speech | NetRoom
Inworld Text to speech

Inworld Realtime TTS-2

Press play and hear Inworld Realtime TTS-2. Then choose the voice that fits.

Voice sample
Svetlana
Ru
0:000:05

Здравствуйте! Так звучит мой голос. Я озвучу ваш текст спокойно и разборчиво.

Every voice reads the same line. · Sample in Russian

Voices133

One line, every voice. Which one is yours?

Voice your text with Svetlana
133Voices
2,000Characters per request
MP3 · WAVFormats
Price

What your project costs

Pick a project
About $0.036
850 characters, about 1 min of speech

The sample line above costs about $0.0034.

The price appears as you type.

Billed by the number of characters in your text. A minute of speech is roughly 850 characters.

Compare

Same line, two voices

Two voices are easier to judge side by side. Pick a pair and hear them back to back.

0:00 / 0:06
0:00 / 0:06

A runs 6.3 s, B runs 5.5 s.

Direction

Write the feeling into the text

Put a tag in square brackets before a line. The voice changes how it speaks. The tag itself is never read aloud.

Tags this model understands
[warm][whispering][excited]
Example text

[warm] I thought this day would never come. [whispering] But here we are, and it worked.

The samples above are plain readings, without tags.

Svetlana0:00 / 0:05
Voice your text
Strengths

What it's the best tool for

  • 133 available voice options
  • Four Russian catalogue voices
  • 0.5×–1.5× speed
  • Delivery cues and MP3/WAV
Limitations

When to reach for something else

  • The form limit is 2,000 characters
  • Speed and cues can affect intelligibility
  • Speech is delivered as a file for further use
Where teams use it

Four scenarios where it pays for itself

01
Character speech
Choose a voice and expressive delivery.
02
Interactive prototype
Prepare short application responses.
03
Russian narration
Compare the available Russian options.
04
Reading pace
Adjust speed to fit a scene or explanation.
About model

More about Inworld Realtime TTS-2

Inworld Realtime TTS-2: speech with cues and speed control

Inworld Realtime TTS-2 generates speech from text using a selected preset voice. The current selection contains 133 voice options, including four Russian choices. Listen to real samples on the page and choose a delivery for a character, explanation or interactive line.

Available in NetRoom

NetRoom supports delivery cues and speed from 0.5× to 1.5×. MP3 and WAV files are available, with a form limit of 2,000 characters. Choose the required language and sound from the offered voice options. The result is an audio file ready to use in your project.

Preparing the result

Begin with a short phrase in the required language. Choose a voice and adjust speed in small steps while checking intelligibility. Test one expressive cue at a time on an individual line. For longer material, keep settings consistent and review joins between files.

Practical uses

  • Character speech: Choose a voice and expressive delivery.
  • Interactive prototype: Prepare short application responses.
  • Russian narration: Compare the available Russian options.
  • Reading pace: Adjust speed to fit a scene or explanation.

Reviewing the result

The form limit is 2,000 characters; Speed and cues can affect intelligibility; Speech is delivered as a file for further use.

Recent changes

What changed Inworld Realtime TTS-2

Full changelog →

Use Inworld Realtime TTS-2 via the API

The same engine, straight from your code: one key and one balance for text, images, video and sound. Pay only for the requests you make.

curl
curl https://netroom.ai/api/v1/generations \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "inworld/inworld-tts-2", "input": {"text": "Hello! This is how my voice sounds.", "voice": "Svetlana", "output_format": "MP3"}}'

The model id is already in the example. The full parameter reference and prices live in GET /api/v1/models and in the docs.

API documentation Get an API key

Pick a voice.
Paste your text.

Samples are free to listen to. You pay only for what you generate.