MAI-Voice 2.1 — text-to-speech | NetRoom
Microsoft Text to speech

Microsoft MAI-Voice 2.1

Press play and hear Microsoft MAI-Voice 2.1. Then choose the voice that fits.

Voice sample
ru-RU-Masha
0:000:07

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

Every voice reads the same line. · Sample in Russian

Voices97

One line, every voice. Which one is yours?

Voice your text with ru-RU-Masha
97Voices
5,000Characters per request
MP3 · WAVFormats
Price

What your project costs

Pick a project
About $0.02
750 characters, about 1 min of speech

The sample line above costs about $0.0021.

The price appears as you type.

Billed by the number of characters in your text. A minute of speech is roughly 750 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 / 0:07

A runs 5.6 s, B runs 7.1 s.

ru-RU-Masha0:00 / 0:07
Voice your text
Strengths

What it's the best tool for

  • 97 voice-and-language choices
  • Auditions before selection
  • Controls matched to the selected voice
  • MP3 and WAV for further editing
Limitations

When to reach for something else

  • Split long text to fit the form limit
  • The voice sets the locale
  • Review names and joins between sections
Where teams use it

Four scenarios where it pays for itself

01
Audiobook
Choose a narrative voice and divide the text into sections.
02
Lecture
Check terminology and the reading of numerical data.
03
Brand narration
Compare the same line across voices.
04
Explainer video
Prepare speech for your video editor.
About model

More about Microsoft MAI-Voice 2.1

MAI-Voice 2.1: narration and longer-form speech

Microsoft MAI-Voice 2.1 reads prepared narration, explanations and other text aloud. The page offers 97 available voice-and-language options with real samples. Choose by how your material sounds: a calm story and a service message need different delivery.

Available in NetRoom

Select the complete voice option with its locale rather than relying on an abstract model-language setting. Delivery and supported styles follow that choice. Speech is available as MP3 or WAV, with a form limit of 5,000 characters per request. Split longer material into meaningful sections and keep pronunciation rules consistent.

Preparing the result

Test an opening line, a difficult name and a sentence with numbers in one short excerpt. Then read the material in sections using the same voice choice. Review joins so pauses do not interrupt the narrative. The page lets you compare real voices without resynthesising the same audition phrase.

Practical uses

  • Audiobook: Choose a narrative voice and divide the text into sections.
  • Lecture: Check terminology and the reading of numerical data.
  • Brand narration: Compare the same line across voices.
  • Explainer video: Prepare speech for your video editor.

Reviewing the result

Split long text to fit the form limit; The voice sets the locale; Review names and joins between sections.

Recent changes

What changed Microsoft MAI-Voice 2.1

Full changelog →

Use Microsoft MAI-Voice 2.1 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": "microsoft/mai-voice-21", "input": {"text": "Hello! This is how my voice sounds.", "voice": "ru-RU-Masha:MAI-Voice-2.1", "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.