Cloud and progress make audio guides free

Speech synthesis in the cloud makes professional audio guides free and accessible to every institution.

Audio guides are amazing! While you are consuming them, you can look at the beautiful landscape or marvel at an exciting exhibition object.

What is holding many back from offering an AudioGuide? While texts can be typed quickly, audio requires much more effort:

  • Really good and crisp texts,
  • which are then read by professional speakers and
  • are recorded with good equipment,
  • which also requires a lot of specialist knowledge.

Does it have to be expensive? Not at all. Now you can get great speakers in many languages for free. For free.

We would like to introduce you to Amazon Polly. Polly is in a way Alexa’s sister and reads out any text that you put into a form field. Much more: You can also download the read text as an MP3 file.

What you need is an Amazon account that you can use to register for Amazon Web Services. Once the account has been created, Polly can be found here: console.aws.amazon.com/polly. In the following video, we would like to show you what Polly can do.

The pricing is intriguing. It costs four to 16 $ per million characters per account – that’s 23:08 hours, according to Amazon. A four-minute contribution would cost just one cent if it weren’t for the free limit that Amazon gives everyone each month: The first 5 million characters of text readout are completely free.

Of course, such recordings never match the stunning quality of trained speakers. But the computer voice from the cloud has even more advantages besides the price:

  • High production costs and long lead times usually kill any audio project before it even starts. Polly not only takes care of a quick start but also masters later changes in no time: change text, copy into the input field, download MP3 file. Done.
  • Time to market: there are no more excuses and postponements. In a few minutes, the first test will be read out loud and is already available as an MP3 file. Sit down, type, done.
  • Constant improvements: You can listen to this over and over again while working and optimize the spoken text and its flow.
  • Many languages: You have only a few guests or visitors from China or Korea and want to offer them the audio guide as well. All you need is a translator and no speaker. Polly is fluent in over 20 languages ​​(from Arabic to Welsh) in several accents. Polly also comes in several editions (male and female).
  • Many people do not like their own voice and therefore do not record an audio guide themselves in advance.

Polly solves all of these problems.

This is not 100 percent perfect, but on the one hand, we have already got used to Alexa and Siri. On the other hand, technical progress is on your side, because the quality of the read texts will always be better and certainly not get worse in the future.

Professionals can use SSML (Speech Synthesis Markup Language) to control and fine-tune certain aspects such as volume, pitch or speech speed. You can find out exactly how to do this in a help document.

xamoom finally solves the last problem: offering an audio guide on the mobile web (users don’t need anything extra) or via an app. Prices start at 199 euros per month.

Get started today

Try for your own what xamoom can do to unleash new revenue potential for your business.

logo xamoom