Timed pauses in the text
Markers set pauses from 0.01 up to 99.99 seconds, with up to two decimal places.
Turn text into speech
MiniMax Speech 2.6 [Turbo]
Generate speech from text prompts and different voices using the MiniMax Speech-2.6 HD model, which leverages advanced AI techniques to create high-quality text-to-speech.
Made by MiniMax20 creditsper run Pro
Opens the audio studio with MiniMax Speech 2.6 [Turbo] ready to use. You can look around as a guest. Running it takes the Pro plan or higher.
What MiniMax Speech 2.6 [Turbo] makes, what it needs and what you get
What it makes
Turn text into speech
Reads your text aloud in a natural-sounding voice.
What you need
- The text to speak
What you get
A spoken audio clip of your text
About MiniMax Speech 2.6 [Turbo]
MiniMax Speech 2.6 [Turbo] turns the text you type into a spoken audio file. The text can carry paragraph breaks and pause markers, so you can set the length of each pause.
A pause marker looks like <#x#>. Replace x with a number of seconds between 0.01 and 99.99, using no more than two decimal places. A marker must sit between two pieces of speakable text. Two markers in a row are not allowed. Paragraph breaks are marked by starting a new line.
The voice can be changed with Voice Speed, Voice Volume, Voice Pitch and Voice Emotion. Language Boost lets you name a language to be recognised better. The file has Audio Format, Sample Rate, Bitrate and Channel settings. The price is 20 credits. MiniMax Speech 2.6 [HD] accepts the same text and has the same settings and price.
Other models for this job
Same job: turn text into speech. Compare before you choose.
Audio Pro Open
CSM-1BTurn text into speech
CSM (Conversational Speech Model) is a speech generation model from Sesame that generates RVQ audio codes from text and audio inputs.
Sesame100 creditsper run
Audio Pro Open
Kokoro TTS (Hindi)Turn text into speech
A fast and expressive Hindi text-to-speech model with clear pronunciation and accurate intonation.
Open Source100 creditsper run
Audio Pro Open
Kokoro TTS (Mandarin Chinese)Turn text into speech
A highly efficient Mandarin Chinese text-to-speech model that captures natural tones and prosody.
Open Source100 creditsper run
Audio Pro Open
Kokoro TTS (Japanese)Turn text into speech
A fast and natural-sounding Japanese text-to-speech model optimized for smooth pronunciation.
Open Source100 creditsper run
What it does well
Paragraph breaks
A new line in the text marks a paragraph break.
Speed, volume and pitch
Voice Speed goes from 0.5 to 2, Voice Volume from 0.01 to 10 and Voice Pitch from -12 to 12.
Seven voice emotions
Voice Emotion has seven choices, including angry, fearful and surprised.
How to use MiniMax Speech 2.6 [Turbo]
How It Works
How It Works
01
Type the text
Enter what you want spoken in Prompt, using new lines for paragraph breaks.
02
Mark the pauses
Where you want a pause, add a marker like <#x#> between two pieces of text.
03
Set the options and generate
Choose the voice and file settings, then generate the audio file.
Tip Markers cannot be used one after another, so keep speakable text between them.
Good for
Audio for a video script
Write the lines, mark the pauses, and get a spoken track.
A spoken announcement
Turn a written message into audio, with pauses where you need them.
Questions
Quick answers to help you get the most out of MiniMax Speech 2.6 [Turbo] in FunAI Studio.
1. Can I control pauses?
2. Can I change the emotion?
3. How much does it cost?