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

Microsoft MAI-Voice 2.1 Flash

Press play and hear Microsoft MAI-Voice 2.1 Flash. 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 $0.013
700 characters, about 1 min of speech

The sample line above costs about $0.0014.

The price appears as you type.

Billed by the number of characters in your text. A minute of speech is roughly 700 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 / 0:09

A runs 5.6 s, B runs 9.1 s.

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

What it's the best tool for

  • 97 voice-and-language options
  • Russian catalogue voices
  • Voice-specific speaking styles
  • MP3 and WAV
Limitations

When to reach for something else

  • Locale follows the voice option
  • Speaking styles are voice-dependent
  • Up to 5,000 characters per request
Where teams use it

Four scenarios where it pays for itself

01
Voice interface
Prepare short responses for an interactive workflow.
02
Service line
Check clarity of names and instructions.
03
Learning step
Read one complete step in a process.
04
Localisation
Select a voice with the required locale.
About model

More about Microsoft MAI-Voice 2.1 Flash

MAI-Voice 2.1 Flash: speech with voice and locale selection

Microsoft MAI-Voice 2.1 Flash converts text to speech using preset voices. The current catalogue contains 97 voice-and-language options, including Russian choices. Flash targets short interactive lines; audition each option using a playable real sample on the page.

Available in NetRoom

The selected voice determines the locale, so choose a matching Russian voice for Russian material. Available speaking styles depend on the particular voice; use its listed controls. MP3 and WAV output are available, with up to 5,000 characters per form request.

Preparing the result

Choose the locale and voice before testing a short line containing your own terminology. Keep wording clear and write numbers in a spoken-friendly form. Do not assume a style from one voice applies to another. Listen through the whole line and assess its pauses before use.

Practical uses

  • Voice interface: Prepare short responses for an interactive workflow.
  • Service line: Check clarity of names and instructions.
  • Learning step: Read one complete step in a process.
  • Localisation: Select a voice with the required locale.

Reviewing the result

Locale follows the voice option; Speaking styles are voice-dependent; Up to 5,000 characters per request.

Recent changes

What changed Microsoft MAI-Voice 2.1 Flash

Full changelog →

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