Text goes in the Scene input
The required Scene input holds the text you want turned into audio.
Turn text into speech
CSM-1B
CSM (Conversational Speech Model) is a speech generation model from Sesame that generates RVQ audio codes from text and audio inputs.
Made by Sesame100 creditsper run Pro
Opens the audio studio with CSM-1B ready to use. You can look around as a guest. Running it takes the Pro plan or higher.
What CSM-1B 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
You also make one choice about how it runs.
What you get
A spoken audio clip of your text
About CSM-1B
CSM-1B is a speech generation model from Sesame. CSM stands for Conversational Speech Model. It turns text into an audio clip, and you get the generated audio back.
The Scene input is required: it holds the text you want turned into audio. The Context input is optional, and you can leave it empty.
Choose CSM-1B when you want speech made from written text and you only need to fill in one input. A run costs 100 credits.
Other models for this job
Same job: turn text into speech. Compare before you choose.
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
Audio Pro Open
Kokoro TTS (Italian)Turn text into speech
A high-quality Italian text-to-speech model delivering smooth and expressive speech synthesis.
Open Source100 creditsper run
What it does well
Optional Context input
Context is optional. You can leave it empty.
How to use CSM-1B
How It Works
How It Works
01
Enter the Scene
Type the text you want turned into audio in the Scene input.
02
Check Context
Context is optional and can be left empty.
03
Generate and listen
Run the model. A run costs 100 credits and returns the generated audio.
Tip Scene is the only required input.
Good for
Speech from written text
Enter your text as the Scene and get spoken audio back.
Questions
Quick answers to help you get the most out of CSM-1B in FunAI Studio.
1. What do I need to provide?
2. What do I get back?
3. How much does it cost?