Tags like (laughs) and (sighs)
The text can include (laughs), (sighs), (coughs), (clears throat), (gasps), (sniffs), (groans) and (yawns).
Turn text into speech
MiniMax Speech 2.8 [HD]
Generate speech from text prompts and different voices using the MiniMax Speech-2.8 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 2.8 [HD] ready to use. You can look around as a guest. Running it takes the Pro plan or higher.
What MiniMax Speech 2.8 [HD] 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 2.8 [HD]
MiniMax Speech 2.8 [HD] reads your text aloud and accepts tags written inside it. The tags are (laughs), (sighs), (coughs), (clears throat), (gasps), (sniffs), (groans) and (yawns). You can also add a pause with <#x#>, where x is a length of 0.01 to 99.99 seconds.
Text is all you must provide. The voice ranges are speed 0.5 to 2, volume 0.01 to 10 and pitch -12 to 12. Voice Emotion offers seven choices. With Language Boost you can name one of ten languages, from Chinese to Turkish, to improve its recognition.
You get an audio file back. Audio Format, Sample Rate, Bitrate and Channel are the file settings. MiniMax Speech 2.8 [HD] costs 20 credits. MiniMax Speech 2.8 [Turbo] has the same inputs, tags and settings, and costs 20 credits too.
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
Pauses of your choosing
Add <#x#> with x from 0.01 to 99.99 seconds.
Speed, volume and pitch ranges
Voice Speed spans 0.5 to 2, Voice Volume 0.01 to 10 and Voice Pitch -12 to 12.
Ten Language Boost choices
Choose a language, from Chinese to Turkish, to improve recognition of it.
How to use MiniMax Speech 2.8 [HD]
How It Works
How It Works
01
Write the text
Enter the words to be spoken in Prompt.
02
Add tags and pauses
Place a tag such as (laughs) in the text, and use <#x#> for pauses of 0.01 to 99.99 seconds.
03
Adjust and generate
Set the voice and file options you want, then generate the audio.
Tip Write each tag in parentheses, for example (clears throat).
Good for
Spoken lines with reactions
Add tags like (laughs) or (sighs) to a line of speech.
Read-aloud scripts with pauses
Place pause markers in a script and get it back as audio.
Questions
Quick answers to help you get the most out of MiniMax Speech 2.8 [HD] in FunAI Studio.
1. Which tags can I use?
2. How do I set a pause length?
3. What does it cost?