In November 2019, we announced the availability of new Alexa speaking styles for news and music content in your skills. Today, we are excited to introduce three new capabilities that will help create a more natural and intuitive voice experience for your customers:
You can learn more about these new capabilities in our technical documentation.
The new long-form speaking style (available in the US only) can help customers engage with large amounts of content or information such as articles, podcasts and other longer form content. For example, you can use this speaking style for customers who want to have the content on a web page read to them or listen to a storytelling section in a game. Powered by a deep-learning text-to-speech model, the long-form speaking style enables Alexa to speak with more natural pauses while going from one paragraph to the next or even from one dialog to another between different characters. Check out the technical documentation for the long-form speaking style and compare the neutral audio sample and the long-form speaking style audio sample below.
Neutral | Long-form Speaking Style | |
Audio Sample | Audio Sample |
To implement the long-form speaking style, you can use the syntax below:
<amazon:domain name="long-form">text</amazon:domain>
<speak>
<amazon:domain name="long-form">
Meet Echo Dot. Our most popular Echo is now even better.
With a new speaker and design, Echo Dot is a voice-controlled smart speaker with Alexa, perfect for any room. Just ask for music, news, information, and more. You can also call almost anyone and control compatible smart home devices with your voice.
</amazon:domain>
</speak>
Using Amazon Polly voices in your skills can create a more engaging and enhanced customer experience. For example, the My Spaceship Alexa skill enables an unique customer experience with its use of multiple characters with different Amazon Polly voices. Starting today, you can also use the news and conversational speaking styles in two Amazon Polly voices: Matthew and Joanna. Additionally, you can use the news speaking style in the US Spanish Amazon Polly voice, Lupe. The news speaking style makes the Matthew, Joanna, and Lupe voices sound similar to what you hear from TV news anchors and radio hosts, while the conversational speaking style makes the Matthew and Joanna voices sound less formal and as if they’re speaking to friends and family. The conversational speaking style is only available in select Polly voices and not Alexa’s voice. Compare the neutral Polly voices and the Polly voices with speaking styles below:
Neutral | Speaking Style | |
Joanna - News | Audio Sample | Audio Sample |
Joanna - Conversational | Audio Sample | Audio Sample |
Matthew - News | Audio Sample | Audio Sample |
Matthew - Conversational | Audio Sample | Audio Sample |
Lupe - News | Audio Sample | Audio Sample |
To implement speaking styles in Amazon Polly voices, you can use the syntax below:
<speak>
<voice name="Joanna">
<amazon:domain name="news">With the new world of social distancing and stay-at-home orders in place for most of the country, customers have generated unprecedented demand for grocery delivery.</amazon:domain>
</voice>
</speak>
You can also use speaking styles in multiple Amazon Polly voices in the same response:
<speak>
<voice name="Matthew">
<amazon:domain name="news">
Latest news: The conversational and news styles are now available for the Matthew or Joanna voices!
</amazon:domain>
</voice>
<voice name="Joanna">
<amazon:domain name="conversational">
That was all for today. Thank you.
</amazon:domain>
</voice>
</speak>
Finally, starting today you can also use 10 additonal Amazon Polly voices in 6 new languages (es-US, es-MX, fr-CA, pt-BR, es-ES, and it-IT). To implement new voices, check out the technical documentation.
<speak>
<lang xml:lang="es-US">
<voice name="Penelope">Hola! Mi nombre es Penélope.</voice>
<voice name="Lupe">Hola! Mi nombre es Lupe.</voice>
<voice name="Miguel">Hola! Mi nombre es Miguel.</voice>
</lang>
</speak>
<speak>
<lang xml:lang="es-MX">
<voice name="Mia">¡Hola! Me llamo Mía.</voice>
</lang>
</speak>
<speak>
<lang xml:lang="fr-CA">
<voice name="Chantal">Salut, je m'appelle Chantal.</voice>
</lang>
</speak>
<speak>
<lang xml:lang="pt-BR">
<voice name="Vitoria">Olá, meu nome é Vitória.</voice>
<voice name="Camila">Olá, meu nome é Camila.</voice>
<voice name="Ricardo">Olá, meu nome é Ricardo.</voice>
</lang>
</speak>
<speak>
<lang xml:lang="es-ES">
<voice name="Lucia">¡Hola! Me llamo Lucía.</voice>
</lang>
<lang xml:lang="it-IT">
<voice name="Bianca">Ciao! Mi chiamo Bianca.</voice>
</lang>
</speak>
Additional Amazon Polly Voices | |
Penélope | Audio Sample |
Lupe | Audio Sample |
Miguel | Audio Sample |
Mía | Audio Sample |
Chantal | Audio Sample |
Vitória | Audio Sample |
Camila | Audio Sample |
Ricardo | Audio Sample |
Lucía | Audio Sample |
Bianca | Audio Sample |
We look forward to seeing what you build with the new long-form speaking style and Amazon Polly voices. Please ask questions and share your feedback on the Alexa developer forum. And feel free to connect with the Alexa Text-to-Speech Product Manager, Nikhil, on linkedin.