Voxtral TTS 3 — text-to-speech | NetRoom
Mistralai Text to speech

Mistral Voxtral TTS 3

Press play and hear Mistral Voxtral TTS 3. Then choose the voice that fits.

Voice sample
Voice 3150
0:000:05

Hello! This is how my voice sounds. I will read your text clearly and naturally.

Every voice reads the same line.

Voices66

One line, every voice. Which one is yours?

Voice your text with Voice 3150
66Voices
5,000Characters per request
MP3 · WAVFormats
Price

What your project costs

Pick a project
About $0.016
1,000 characters, about 1 min of speech

The sample line above costs about $0.0012.

The price appears as you type.

Billed by the number of characters in your text. A minute of speech is roughly 1,000 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 / 0:05
0:00 / 0:05

A runs 5.4 s, B runs 4.9 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
[happy][sad][whispering][excited]
Example text

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

The samples above are plain readings, without tags.

Voice 31500:00 / 0:05
Voice your text
Strengths

What it's the best tool for

  • 66 voice options
  • Emotion and pacing cues
  • Real auditions on the page
  • MP3 and WAV
Limitations

When to reach for something else

  • Cue effects depend on text and voice
  • Up to 5,000 characters per request
  • Samples do not establish quality for every accent
Where teams use it

Four scenarios where it pays for itself

01
Character line
Compare neutral and emotional delivery.
02
Expressive narration
Test the desired narrative tone.
03
Game or prototype
Prepare individual speech clips for editing.
04
Localised speech
Listen through difficult words in the required language.
About model

More about Mistral Voxtral TTS 3

Voxtral TTS 3: speech with emotion cues

Mistral Voxtral TTS 3 turns text into speech and accepts emotion and pacing cues in the text. NetRoom’s current catalogue contains 66 voice options with real auditions. It is useful for character lines, expressive narration and comparing alternative delivery choices.

Available in NetRoom

Choose a preset voice, then test the intended cue on a short line. Text-based delivery guidance does not guarantee an identical emotional effect for every sentence. NetRoom offers MP3 and WAV, with up to 5,000 characters per form request. These samples use this model’s catalogue voices without cloning another person’s speech.

Preparing the result

Keep spoken wording clear and avoid combining contradictory emotional cues. Compare a neutral version and an expressive version of the same excerpt. For several characters, prepare and edit separate tracks when the form does not offer the required dialogue workflow. Listen through the final file.

Practical uses

  • Character line: Compare neutral and emotional delivery.
  • Expressive narration: Test the desired narrative tone.
  • Game or prototype: Prepare individual speech clips for editing.
  • Localised speech: Listen through difficult words in the required language.

Reviewing the result

Cue effects depend on text and voice; Up to 5,000 characters per request; Samples do not establish quality for every accent.

Recent changes

What changed Mistral Voxtral TTS 3

Full changelog →

Use Mistral Voxtral TTS 3 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": "mistralai/voxtral-tts-3", "input": {"text": "Hello! This is how my voice sounds.", "voice": "voice_3150", "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.