Wolfram Language

Synthesize Speech

Use SpeechSynthesize to generate audio from text, general expressions, formulas and more. The generated audio can be processed, analyzed or programmatically played back.

Synthesize speech from a text string.

In[1]:=1
Out[1]=1

Synthesize speech from an expression.

In[2]:=2
Out[2]=2

Display the waveform and spectrogram of the synthesized signal.

In[3]:=3
Out[3]=3
In[4]:=4
Out[4]=4

SpeechSynthesize can use different voice styles for synthesis. Select a voice from $VoiceStyles.

In[5]:=5
Out[5]=5

Repeat the synthesis using the chosen voice.

In[6]:=6
Out[6]=6
In[7]:=7
Out[7]=7

Related Examples

Find out if you already have access to Wolfram tech through your organization
×