Generate TTS Using Your Terminal

It’s not a new hack but it will work well if you have short texts (1-3 sentences) that you wish to convert to speech.

After all, when returning a response to the Google Assistant, you can use a subset of the Speech Synthesis Markup Language (SSML).

Why?

Because you can make your agent’s responses seem more life-like experience.

How?

Open your terminal and try something like this:

curl "http://www.google.com/speech-api/v1/synthesize?lang=en-us&text=actions+on+google+rock" -o aog-rock-hack.mp3

That’s it.

If you want to use SSML and get fancy, it’s also support it in the request:

https://www.google.com/speech-api/v1/synthesize?lang=es-US&ssml=<speak>Hey<prosody%20rate="slow">how+are+you+doing+this+morning</prosody></speak>

Later you can use it in your Action on Google like that:

	<speak>
	Here are <say-as interpret-as="characters">SSML</say-as> samples.
	I can pause <break time="3s"/>.
	I can play a sound
	<audio src="https://www.example.com/MY_MP3_FILE.mp3">
	didn't get your MP3 audio file
	</audio>.
	I can speak in cardinals. Your number is
	<say-as interpret-as="cardinal">
	10
	</say-as>.
	Or I can speak in ordinals. You are
	<say-as interpret-as="ordinal">
	10
	</say-as> in line.
	Or I can even speak in digits. The digits for ten are
	<say-as interpret-as="characters">
	10
	</say-as>.
	I can also substitute phrases, like the
	<sub alias="World Wide Web Consortium">
	W3C
	</sub>.
	Finally, I can speak a paragraph with two sentences.
	<p>
	<s>This is sentence one.</s>
	<s>This is sentence two.</s>
	</p>
	</speak>

view raw AoG-SSML-example.html hosted with ❤ by GitHub

For more hack and tips, check these slides on VUI Design or the official docs on SSML.

Advertisement