Many clips in one run
Batch mode takes a list of texts and a list of voice descriptions and returns one audio file for each text.
Turn text into speech
Maya batch
Maya1 is a state-of-the-art speech model by Maya Research for expressive voice generation, built to capture real human emotion and precise voice design.
Made by Open Source100 creditsper 5 s Pro
Opens the audio studio with Maya batch ready to use. You can look around as a guest. Running it takes the Pro plan or higher.
What Maya batch 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
- WAV and MP3 files
About Maya batch
Maya batch turns text into expressive speech and can make several clips in one run. In batch mode you enter a list of texts and a matching list of voice descriptions. You get back a list of audio files.
Texts holds the lines to speak. Prompts holds one voice description for each line, so both lists must be the same length. A description can cover age, accent, pitch, pacing, tone and intensity. Inside any text you can add emotion tags. Write the emotion word in angle brackets, such as laugh, whisper or excited. Maya batch also has a stream mode that takes one Text and one Prompt instead of lists.
Temperature (0 to 2, starting at 0.4) and Sample Rate apply to every clip. Lower Temperature values from 0.2 to 0.5 give more stable audio, and higher values add variation. Sample Rate offers 48 kHz (kilohertz) for higher quality or 24 kHz for faster results. Batch mode starts at 48 kHz and stream mode at 24 kHz. Maya batch costs about 100 credits for 5s. Maya1 tts costs the same but works on one text at a time.
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
One voice description per text
Prompts holds one voice description for each text, covering things like age, accent, pitch, pacing, tone and intensity.
Emotion tags in every text
Add tags such as sigh or giggle, each in angle brackets, inside any text in your list. Seventeen emotions are available.
How to use Maya batch
How It Works
How It Works
01
Write your texts
Enter the lines to speak in Texts. Add emotion tags such as excited, in angle brackets, where you want them.
02
Describe each voice
In Prompts, add one voice description for each text. Both lists must have the same length.
03
Generate and listen
Change Temperature or Sample Rate if you like, run the model, and play the audio file for each text.
Tip For a single clip, use stream mode, which takes one Text and one Prompt.
Good for
Character dialogue
Give each line of a script its own voice description and make all the clips in one run.
Several announcements at once
Voice a set of short messages together instead of one by one.
Questions
Quick answers to help you get the most out of Maya batch in FunAI Studio.
1. What do I need to provide in batch mode?
2. What is the difference between batch and stream mode?
3. How much does Maya batch cost?