Microsoft MAI-Voice 2.1 Flash
Press play and hear Microsoft MAI-Voice 2.1 Flash. Then choose the voice that fits.
Здравствуйте! Так звучит мой голос. Я озвучу ваш текст спокойно и разборчиво.
Voices97
No voice matches.
One line, every voice. Which one is yours?
Voice your text with ru-RU-MashaWhat your project costs
The sample line above costs about $0.0014.
Billed by the number of characters in your text. A minute of speech is roughly 700 characters.
Same line, two voices
Two voices are easier to judge side by side. Pick a pair and hear them back to back.
A runs 5.6 s, B runs 9.1 s.
What it's the best tool for
- 97 voice-and-language options
- Russian catalogue voices
- Voice-specific speaking styles
- MP3 and WAV
When to reach for something else
- Locale follows the voice option
- Speaking styles are voice-dependent
- Up to 5,000 characters per request
Four scenarios where it pays for itself
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.
What changed Microsoft MAI-Voice 2.1 Flash
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 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.
Pick a voice.
Paste your text.
Samples are free to listen to. You pay only for what you generate.