Emotional overtones in synthesized speech: how Dasha makes your AI conversations ever more human-like

Better yet, you are not limited to predefining emotions. Instead, you can instruct Dasha to extract information about the emotion from the text you give us. So you are free to find an exact emotion that works best for you! Here are some examples for you to better understand the importance of emotional speech synthesis.

Let's say you came home after a long day and speak with your Dasha-based Home Assistant that you had written yourself:

John Doe: Hey, Dasha. It was a hard day. Would you mind dimming the light?
AI with sorrowful emotion: I'm sorry to hear that. I'll dim the light. Do you need anything else?

Or, for example, you want to make an answering machine which angrily tells the caller not to call back after the caller is identified as a telemarketer:

Caller: Hi, I'd like you to buy something you don’t need.
AI with angry emotion: No! Do not call here ever again!

Try it yourself in 2 simple steps: (Install Dasha CLI)[https://docs.dasha.ai/en-us/default/getting-started/#step-1-installing-dasha-cli], run:

npm i -g @dasha.ai/cli

Run:

dasha tts synthesize \
--provider-name dasha-emotional \
--speaker "Kate" \
--emotion "from text: I am so sorry." \
"I'm sorry to hear that. I'll dim the light. Do you need anything else?" -o sorry.mp3
dasha tts synthesize \
--provider-name dasha-emotional \
--speaker "Kate" \
--emotion "from text: You are so stupid! And I’m mad!" \
"I'm sorry to hear that. I'll dim the light. Do you need anything else?" -o angry.mp3

You can play with text in emotion argument to get the emotional speech you want.

Looking for a more sophisticated way to use Emotional Speech Synthesis in your Dasha App? Read up on our Emotional Speech Synthesis Docs.