Talestreamer is HTML for voice.

Talestreamer makes your voicebot sound great by replacing the default TTS engine with rich, multilayered audio that incorporates synthesized speech, human voices, and foreground and background music and sound effects. You control the responses Talestreamer generates using HTML-like content markup (TSML) and CSS-like styling information (TSSS). You integrate your voicebot with Talestreamer to begin using Talestreamer audio files or using Talestreamer’s API. This document describes what Talestreamer can do, how you use it, and how to get started.

Are you building an Alexa skill or a Google Action using NodeJS? Making your skill sound awesome with Talestreamer is an easy 3 step process. Learn more about our Alexa and Actions on Google integration!

What Talestreamer Can Do
Integration
Examples
Reference
FAQ

What Talestreamer Can Do

Talestreamer is a cloud-based service that generates sound as output given an input document. Talestreamer’s output is optimized for Alexa, Google Assistant, and other voicebot ecosystems. Talestreamer input documents are XML. Let’s start with an example:

<br><stream xmlns="http://talestreamer.ai/schema/tsml"><br>  Welcome to Talestreamer!<br></stream><br>

This input document tells Talestreamer to speak the words “Welcome to Talestreamer” in Talestreamer’s default voice (Amy from Amazon Polly). You can paste this document into the Talestreamer Composer and hit the play button to hear the response. You can also download the response and use it directly in your voicebot. Talestreamer reads this input document, calls Amazon Polly to synthesize speech, adjusts the response volume to work with voicebots, and converts Polly’s response a common voicebot audio format.

Talestreamer takes the grunt work out of this simple task. Taking the grunt work out of creating great sounding audio interfaces for voicebots is Talestreamer’s mission in life.

Voice Styling

Let’s look at another way Talestreamer helps you make great sounding audio interfaces: by controlling the style of the response.

<br><stream xmlns="http://talestreamer.ai/schema/tsml" style="voice: Brian"><br>   Welcome to Talestreamer!<br></stream><br>

This input document speaks the same words as before, but in a different style, using the voice of Brian from Amazon Polly. Talestreamer documents separate what is presented (content description) from how it is presented (content styling), a foundational design approach on the web. TSML documents represent styling information, including what voice to use, using Talestreamer Stylesheets (TSSS) syntax in the style attribute.

<br><stream xmlns="http://talestreamer.ai/schema/tsml" style="voice: Miguel"><br>  ¡Bienvenidos a Télstrimer!<br></stream><br>

Talestreamer gives you access to all of the Amazon Polly voices and languages.

Incorporating Human Voices and Sound Effects

<br><stream><br>  <audio src="http://s3.amazonaws.com/magicdoor.huntwork.net/library/TS_INTRO_1_PART_LOGO_START.mp3"></audio><br>  <audio src="http://s3.amazonaws.com/magicdoor.huntwork.net/library/mel_welcome.mp3"></audio><br>  <audio src="http://s3.amazonaws.com/magicdoor.huntwork.net/library/TS_INTRO_1_PART_LOGO_END.mp3"></audio><br></stream><br>

Talestreamer also helps you incorporate human voices and sound effects into your audio interface. Talestreamer can read MP3 audio from any URL, automatically adjust its volume to work with Alexa or Google Assistant, and convert it into their format.

Background Sound and Music

Talestreamer helps you add background audio to your stream.

<br><stream xmlns="http://talestreamer.ai/schema/tsml"><br>  <span style="background-sound: https://s3.amazonaws.com/magicdoor.huntwork.net/library/ts_intro/bg.mp3; background-volume: loud"><br>    Welcome to Talestreamer by The Magic Door. Let’s get started.<br>  </span><br></stream><br>

Talestreamer plays the background sound you specify until the foreground completes, and loops the background sound if it is shorter than the foreground sound.

Composing a Response

You can combine all of these capabilities in a single response.

<br><stream xmlns="http://talestreamer.ai/schema/tsml" style="volume-profile: prenormalized"><br>  <audio src="http://s3.amazonaws.com/magicdoor.huntwork.net/library/TS_INTRO_1_PART_LOGO_START.mp3"></audio><br>  <span style="background-sound: https://s3.amazonaws.com/magicdoor.huntwork.net/library/ts_intro/bg.mp3; background-volume: loud"><br>    <audio src="http://s3.amazonaws.com/magicdoor.huntwork.net/library/MagicDoor_GhostCaptain.mp3" style="start: 146; end: 151.3; volume: 5db"></audio><br>    <span style="break: 0.5s"></span><br>    <span style="voice: Amy">You can add audible personality, branding, and emotion to your voice bot, using Talestreamer.</span><br>    <span style="break: 0.5s"></span><br>    <span style="voice: Raveena">We’re all here to help. Let’s get started!</span><br>    <span style="break: 0.1s"></span><br>  </span><br>  <audio src="http://s3.amazonaws.com/magicdoor.huntwork.net/library/TS_INTRO_1_PART_LOGO_END.mp3" style="volume: -10db"></audio><br></stream><br>

You can use TSML to add structure to your response, and then style different sections of the document differently using TSSS. When you do this, Talestreamer makes multiple requests to Amazon Polly, loads any audio resources you specified, normalizes volume, combines them all together, and converts the result to Alexa’s or Google Assistant’s audio format.

Separating Style From Content

You can also separate style from content using stylesheets.

<br><stream xmlns="http://talestreamer.ai/schema/tsml"><br>  <head><meta name="generator" content="Hexo 3.8.0"><br>    <style><br>    .intro {<br>      background-sound: url(<a href="https://s3.amazonaws.com/magicdoor.huntwork.net/library/ts_intro/bg.mp3)">https://s3.amazonaws.com/magicdoor.huntwork.net/library/ts_intro/bg.mp3)</a>;<br>      background-volume: loud;<br>    }<br>    </style><br>  </head><br>  <span class="intro"><br>    Welcome to Talestreamer by The Magic Door. Let’s get started.<br>  </span><br></stream><br>

If you do use the style style, you can then change your style independent of your content. For example, you could choose new background sound, or a new voice for your skill, without changing any of your code.

Advanced Topics

Talestreamer also supports the following advanced features:

foreground and background volume
trimming audio files
Pitch and rate of synthesized voices
Raw SSML support

For these topics and others, view our reference documentation.

Integration

Talestreamer generates rich audio for your skill in real time as it is needed. The best approach to using Talestreamer is to call Talestreamer from your skill. If you are building an Alexa skill or a Google Action using Javascript, please follow our integration guide for Alexa or Actions on Google.

Alternative Integration Approach – Using Files

When you can’t call Talestreamer in real time, an alternative is to store Talestreamer audio files in AWS S3 and reference them from your skill’s SSML. It’s fast, cheap, and easy to use S3-hosted files in Alexa skills and Google Assistant agents. To use this approach, do the one-time setup process now, and the audio upload process each time you want a new sound.

One-Time Setup

Create an AWS Account
Create an S3 bucket to store your Talestreamer files in. We’ll use talestreamer.example.com as our bucket name below.

Audio Upload

Compose and test the sound using Talestreamer Composer.
Download the sound. By default, it will be called talestreamer.mp3.
Rename the sound to your desired name, such as example.mp3.
Upload the sound to your S3 bucket.
Make sure you choose to make the file world-readable when you upload it.
Use your sound from your skill or agent with the following snippet:
<audio src="https://s3.amazonaws.com/talestreamer.example.com/example.mp3"/>

Examples

Side By Side Comparison of Talestreamer and Plain Text To Speech

<br>  <stream xmlns="http://talestreamer.ai/schema/tsml" style="volume-profile: prenormalized"><br>  <span style="voice: Amy; break: .5s">This is plain text to speech.</span><br>  <span style="voice: Amy; break: .5s">Welcome to Talestreamer by the Magic Door. You can add audible personality, branding, and emotion to your voice bot, using Talestreamer. We’re all here to help. Let’s get started.</span><br>  <span style="voice: Amy; break: .5s">And this is Talestreamer.</span><br>  <audio src="http://s3.amazonaws.com/magicdoor.huntwork.net/library/TS_INTRO_1_PART_LOGO_START.mp3"></audio><br>  <span style="background-sound: https://s3.amazonaws.com/magicdoor.huntwork.net/library/ts_intro/bg.mp3; background-volume: loud"><br>    <audio src="http://s3.amazonaws.com/magicdoor.huntwork.net/library/MagicDoor_GhostCaptain.mp3" style="start: 146; end: 151.3; volume: 5db"></audio><br>    <span style="break: 0.5s"></span><br>    <span style="voice: Amy">You can add audible personality, branding, and emotion to your voice bot, using Talestreamer.</span><br>    <span style="break: 0.5s"></span><br>    <span style="voice: Raveena">We’re all here to help. Let’s get started!</span><br>    <span style="break: 0.1s"></span><br>  </span><br>  <audio src="http://s3.amazonaws.com/magicdoor.huntwork.net/library/TS_INTRO_1_PART_LOGO_END.mp3" style="volume: -10db"></audio><br></stream><br>

Side By Side Comparison, With an External Stylesheet

<br>  <stream xmlns="http://talestreamer.ai/schema/tsml"><br>  <head><meta name="generator" content="Hexo 3.8.0"><br>    <style><br>      stream {<br>        volume-profile: prenormalized;<br>      }<br>      .narratorBreak {<br>        voice: Matthew;<br>        break: .5s;<br>      }<br>      .narrator {<br>        voice: Matthew;<br>      }<br>      .intro {<br>        background-sound: url(<a href="https://s3.amazonaws.com/magicdoor.huntwork.net/library/ts_intro/bg.mp3)">https://s3.amazonaws.com/magicdoor.huntwork.net/library/ts_intro/bg.mp3)</a>;<br>        background-volume: loud;<br>      }<br>      .pause {<br>        break: .5s;<br>      }<br>      .extra {<br>        voice: Brian;<br>      }<br>      .shortPause {<br>        break: .1s;<br>      }<br>      #welcome {<br>        start: 146;<br>        end: 151.3;<br>        volume: 5db;<br>      }<br>      #trailer {<br>        volume: -10db;<br>      }<br>    </style><br>  </head><br>  <span class="narratorBreak">This is plain text to speech.</span><br>  <span class="narratorBreak">Welcome to Talestreamer by the Magic Door. You can add audible personality, branding, and emotion to your voice bot, using Talestreamer. We’re all here to help. Let’s get started.</span><br>  <span class="narratorBreak">And this is Talestreamer.</span><br>  <audio src="http://s3.amazonaws.com/magicdoor.huntwork.net/library/TS_INTRO_1_PART_LOGO_START.mp3"></audio><br>  <span class="intro"><br>    <audio id="welcome" src="http://s3.amazonaws.com/magicdoor.huntwork.net/library/MagicDoor_GhostCaptain.mp3"></audio><br>    <span class="pause"></span><br>    <span class="narrator">You can add audible personality, branding, and emotion to your voice bot, using Talestreamer.</span><br>    <span class="pause"></span><br>    <span class="extra">We’re all here to help. Let’s get started!</span><br>    <span class="shortPause"></span><br>  </span><br>  <audio id="trailer" src="http://s3.amazonaws.com/magicdoor.huntwork.net/library/TS_INTRO_1_PART_LOGO_END.mp3"></audio><br></stream><br>

Comparing Amazon Polly and Google Cloud Text To Speech Voices

<br><div><br>  <span style="voice: Amy">Talestreamer now supports Google Cloud Text To Speech voices, including Wave net voices. That brings Talestreamer up to 88 voices in 25 languages. Let’s compare some Polly and Google voices.</span><br>  <span style="voice: Salli">Hi. I’m Salli. I’m one of the Polly english voices. I play the priestess in the Rogue’s Choice Alexa skill.</span><br>  <span style="voice: en-US-Wavenet-C">Hi. I’m a wave net voice. I have no name, but I sound pretty cool. Machine learning is fun!</span><br>  <span style="voice: Matthew">I’m Matthew. I’m the toughest of the Polly voices. I can do great batman impressions. Like this: <span style="pitch: x-low; rate: slow">You ever danced with the devil in the pale moonlight?</span></span><br>  <span style="voice: en-US-Wavenet-B">I’m a male wave net voice. Did you know that a single wave net model can be trained to produce several different voices?</span><br>  <span style="voice: Penelope">Me llamo Penelope. Se puede usar voces en español y en otros 24 idiomas con Talestreamer.</span><br>  <span style="voice: es-ES-Standard-A">A pesar de que las voces de Google no tienen nombres, aún pueden contar su historia.</span><br></div><br>

A Scene from The Haunted Lighthouse (A Story from The Magic Door)

<br><stream xmlns="http://talestreamer.ai/schema/tsml"><br>  <span style="background-sound: http://s3.amazonaws.com/magicdoor.huntwork.net/library/Birds-Singing.mp3; background-volume: loud">Ok. Sounds good.  <span style="break: 0.3s"></span> I tell Madame Faro that we are not interested in a new challenge right now.<br>  <span style="voice: Raveena">Suit <span style="rate: slow"> yourselves.<span style="break:0.4s"></span> But. </span> If you happen to <span style="rate:slow"> change your mind.</span> find me <span style="rate: slow"> again.</span> and I’ll tell you a <span style="rate: slow"> most interesting, </span> <span style="rate: x-slow"> and quite chilling</span><span style="rate:slow"> story. </span></span></span><br></stream><br>

<br><stream xmlns="http://talestreamer.ai/schema/tsml" style="volume-profile: prenormalized; voice: Amy"><br>  <audio src="https://s3.amazonaws.com/magicdoor.huntwork.net/library/RIDESHARE_X/RIDESHARE_X_HARD_FX_1.mp3" style="end:0.35s"></audio><br>  <audio src="https://s3.amazonaws.com/magicdoor.huntwork.net/library/RIDESHARE_X/RIDESHARE_X_HARD_FX_2.mp3" style="end:0.2s"></audio><br>  <audio src="https://s3.amazonaws.com/magicdoor.huntwork.net/library/RIDESHARE_X/RIDESHARE_X_HARD_FX_3.mp3" style="end:3s"></audio><br>  Welcome to Rideshare X. You can search for vehicles nearby. If you link your Rideshare X account, you can also reserve them. <span style="break: .3s"></span><br><br>  The closest GLA is 154 feet away at 2121 40th Ave West. Should I reserve it for you or do you want to look for another vehicle?<br><br>  <span style="break: 2s"></span><br><br>  <span style="background-sound: url(https://s3.amazonaws.com/magicdoor.huntwork.net/library/RIDESHARE_X/RIDESHARE_X_BG.mp3); background-volume: loud"><span style="break: 2s"></span>Reserving it now.<span style="break: 8s"></span></span><br>  <audio src="https://s3.amazonaws.com/magicdoor.huntwork.net/library/RIDESHARE_X/RIDESHARE_X_HARD_FX_1.mp3"></audio><br><br>  The vehicle is now reserved for you. for more information, refer to your Rideshare X app.<br>  <audio src="https://s3.amazonaws.com/magicdoor.huntwork.net/library/RIDESHARE_X/RIDESHARE_X_HARD_FX_2.mp3"></audio><br>  <audio src="https://s3.amazonaws.com/magicdoor.huntwork.net/library/RIDESHARE_X/RIDESHARE_X_HARD_FX_3.mp3"></audio><br></stream><br>

A Cave, With Sound Effects and Voices

<br><stream xmlns="http://talestreamer.ai/schema/tsml" style="background-sound: http://s3.amazonaws.com/magicdoor.huntwork.net/sounds/rendering/waterdrops.mp3; background-volume: loud"><br>  <span style="break: 1.5s"></span><br>  <span style="voice: Brian">Hi. I’m Brian</span><br>  <span style="voice: Amy">And I’m Amy. We’re with you today from a cave.</span><span style="break: 1s"></span><br>  <span>We’re going to demonstrate some sounds before the rats get us.<span style="break: 1s"></span> What’s that I hear? A fire truck, in this cave?<br>    <audio src="http://s3.amazonaws.com/magicdoor.huntwork.net/sounds/rendering/airhorn.mp3" style="end: 2s"></audio><br>    <span style="break: 2s"></span><br>    Wow, that was weird. I wonder what’s next…<br>  </span><br>  <span style="voice: Brian"><br>    Well, that’s nothing. I see a pterodactyl coming from that passageway. Duck!<br>    <audio src="http://s3.amazonaws.com/magicdoor.huntwork.net/sounds/rendering/ptero.mp3" style="end: 2.5s"></audio><br>  </span><br>  <span style="break: 1.5s"></span><br>  <span style="voice: Amy">Phew, that was close!</span><br></stream><br>

A Skit, Featuring Matthew, With Background From PartnersInRhyme.com

<br><stream xmlns="http://talestreamer.ai/schema/tsml" style="background-sound: https://www.partnersinrhyme.com/pir/libs/media/1234_Rock_it.wav; background-volume: loud; voice: Matthew"><br>    <span style="break: 2s"></span><br>    Welcome to a tough guy skill.<br>    <span style="break: 1s"></span><br>    Everything we do here is tough. Super tough.<br>    <span style="break: .7s"></span><br>    Especially me. Matthew. The toughest of Amazon Polly voices.<br>    <span style="break: 2s"></span><br></stream><br>

Reference

Talestreamer Markup Language (TSML)

<br><?xml version=”1.0” encoding=”UTF-8”?><br><xsd:schema targetNamespace=”<a href="http://talestreamer.ai/schema/tsml"" target="_blank" rel="noopener">http://talestreamer.ai/schema/tsml"</a> xmlns:ssml=”<a href="http://www.w3.org/2001/10/synthesis"" target="_blank" rel="noopener">http://www.w3.org/2001/10/synthesis"</a><br>  xmlns:xsd=”<a href="http://www.w3.org/2001/XMLSchema"" target="_blank" rel="noopener">http://www.w3.org/2001/XMLSchema"</a> xmlns=”<a href="http://talestreamer.ai/schema/tsml"" target="_blank" rel="noopener">http://talestreamer.ai/schema/tsml"</a><br>      elementFormDefault=”qualified”><br><br>  <xsd:import namespace=”<a href="http://www.w3.org/2001/10/synthesis"" target="_blank" rel="noopener">http://www.w3.org/2001/10/synthesis"</a><br>              schemaLocation=”synthesis.xsd”/><br><br>  <!--
    A TSML audio stream is composed of 0 or more audio blocks. Blocks are 
    played sequentially. Some blocks can contain other blocks. 
  --><br>  <xsd:complexType name=”block.type” mixed=”true”><br>    <xsd:sequence minOccurs=”0” maxOccurs=”unbounded”><br>      <xsd:group ref=”contentElements”/><br>    </xsd:sequence><br>    <xsd:attributeGroup ref=”block.attribs”/><br>  </xsd:complexType><br><br>  <xsd:group name=”contentElements”><br>    <a href="xsd:choice" target="_blank" rel="noopener">xsd:choice</a><br>            <!-- 
              One type of block is a raw SSML element. Such an element is 
              sent to a TTS engine without modification.
               --><br>            <xsd:element ref=”ssml:speak”/><br>            <!--
          Another type of block is an audio tag, which plays audio
          from a resource in the foreground.
            --><br>            <xsd:element ref=”audio”/><br>            <!--
              A span creates hierarchical structure in the document, which
              is useful in combination with TSSS. A span can group together elements
              that should have the same TSSS style.
            --><br>            <xsd:element ref=”span” /><br>    </xsd:choice><br>  </xsd:group><br><br>  <!-- 
    stream is the root element of all TSML documents. 
  --><br>  <xsd:element name=”stream”><br>    <xsd:complexType mixed=”true”><br>      <xsd:sequence minOccurs=”0” maxOccurs=”1”><br>        <xsd:sequence minOccurs=”0” maxOccurs=”1”><br>          <xsd:element ref=”head”/><br>        </xsd:sequence><br>        <xsd:sequence minOccurs=”0” maxOccurs=”unbounded”><br>              <xsd:group ref=”contentElements”/><br>        </xsd:sequence><br>      </xsd:sequence><br>      <xsd:attributeGroup ref=”block.attribs”/><br>    </xsd:complexType><br>  </xsd:element><br>  <!--
    span creates hierarchy in the input document to enable styling with TSSS.
  --><br>  <xsd:element name=”span” type=”block.type”/><br>  <!--
    style contains TSSS to apply to the document
  --><br>  <xsd:element name=”style” type=”xsd:string”/><br><br>  <xsd:element name=”head”><br>    <xsd:complexType mixed=”false”><br>      <a href="xsd:annotation" target="_blank" rel="noopener">xsd:annotation</a><a href="xsd:documentation" target="_blank" rel="noopener">xsd:documentation</a>We allow 1 link element for now, and it must be the first element. We allow 1 style element for now, and it comes after any link elements.</xsd:documentation></xsd:annotation><br>      <xsd:sequence minOccurs=”0” maxOccurs=”1”><br>        <xsd:sequence minOccurs=”0” maxOccurs=”1”><br>          <xsd:element ref=”link”/><br>        </xsd:sequence><br>        <xsd:sequence minOccurs=”0” maxOccurs=”1”><br>          <xsd:element ref=”style”/><br>        </xsd:sequence><br>      </xsd:sequence><br>    </xsd:complexType><br>  </xsd:element><br><br>  <!--
    The TSML audio tag is similar to the SSML audio tag. 
  --><br>  <xsd:element name=”audio”><br>    <a href="xsd:complexType" target="_blank" rel="noopener">xsd:complexType</a><br>      <xsd:attribute name=”src” type=”xsd:anyURI” use=”required”/><br>      <xsd:attributeGroup ref=”block.attribs”/><br>    </xsd:complexType><br>  </xsd:element><br><br>  <!--
    TSML block elements can have style, class, and an ID.
  --><br>  <xsd:attributeGroup name=”block.attribs”><br>        <xsd:attribute name=”id” type=”xsd:ID”/><br>    <xsd:attribute name=”style” type=”xsd:string”/><br>    <xsd:attribute name=”class”><br>      <a href="xsd:simpleType" target="_blank" rel="noopener">xsd:simpleType</a><br>          <xsd:restriction base=”xsd:string”><br>            <xsd:pattern value=”\S+”/><br>          </xsd:restriction><br>      </xsd:simpleType><br>    </xsd:attribute><br>  </xsd:attributeGroup><br></xsd:schema><br>

Talestreamer Stylesheets (TSSS)

<br>InlineStyles =<br>  Style ([ ]* “;” [ ]* Style)* “;”?<br><br>StyleSheet =<br>  WhiteSpace decl:Declaration WhiteSpace rest:Declaration<em> WhiteSpace<br><br>Declaration =<br>  selector:Selector WhiteSpace “{“ WhiteSpace styles:InlineStyles? WhiteSpace “}” WhiteSpace<br><br>Selector =<br>  ElementSelector / ClassSelector / IdSelector<br><br>ElementSelector = [a-zA-Z0-9]+<br><br>ClassSelector = “.”[a-zA-Z0-9]+<br><br>IdSelector = “#”[a-zA-Z0-9]+<br><br>WhiteSpace = [ \n\t]</em><br><br>Style =<br>  // “rate”: controls that rate of speech for synthesized speech. default: medium<br>  “rate” [ ]* “:” [ ]* RateValue<br>  // “voice”: controls the voice used to synthesize speech. default: Amy<br>  | “voice” [ ]* “:” [ ]* Voice<br>  // “pitch”: controls the pitch of speech for synthesize speech. default: medium<br>  | “pitch” [ ]* “:” [ ]* PitchValue<br>  // “volume”: controls the audio volume for foreground audio. default: medium */<br>  | “volume” [ ]* “:” [ ]* VolumeValue<br>  // “background-volume”: controls the audio volume for background audio. default: medium */<br>  | “background-volume” [ ]* “:” [ ]* VolumeValue<br>  // “volume-profile”: controls the volume normalization algorithm to run on foreground audio.<br>  // default: Automatic Gain Control with targets:<br>  // Integrated Loudness: -14dB; True Peak: -2; Loudness Range: 1 */<br>  | “volume-profile” [ ]* “:” [ ]* VolumeProfileValue<br>  // “volume-profile”: controls the volume normalization algorithm to run on background audio.<br>  // default: Automatic Gain Control with targets:<br>  // Integrated Loudness: -14dB; True Peak: -2; Loudness Range: 1 */<br>  | “background-volume-profile” [ ]* “:” [ ]* VolumeProfileValue<br>  // “background-sound”: the sound to play in the background. default: none */<br>  | “background-sound” [ ]* “:” [ ]* Sound<br>  // “start”: how to trim the foreground audio, specifically, where to start playback. default: 0s */<br>  | “start” [ ]* “:” [ ]* Duration<br>  // “end”: how to trim the foreground audio, specifically, where to end playback. default: <end of stream> */<br>  | “end” [ ]* “:” [ ]* Duration<br>  // “background-start”: how to trim the background audio, specifically, where to start playback. default: 0s */<br>  | “background-start” [ ]* “:” [ ]* Duration<br>  // “background-end”: how to trim the background audio, specifically, where to end playback. default: <end of stream> */<br>  | “background-end” [ ]* “:” [ ]* Duration<br>  // “break”: how long to pause after playing this block. default: 0s */<br>  | “break” [ ]* “:” [ ]* Duration<br>  // “pre-break”: how long to pause before playing this block. default: 0s */<br>  | “pre-break” [ ]* “:” [ ]* Duration<br><br>Sound = Url | BareURL | “none”<br><br>PitchValue = “x-low” | “low” | “medium” | “high” | “x-high”<br>VolumeProfileValue = “none” | “prenormalized”<br>VolumeValue = “loud” | “x-loud” | “soft” | “x-soft” | “medium” | “quiet” | “x-quiet”<br>RateValue = “x-slow” | “slow” | “medium” | “fast” | “x-fast”<br>DecibelValue = val:([-]?[0-9]+)[dD][bB]<br>Url = “url(“ val:[^)]+ “)”<br>BareURL = “http” “s”? “://“ [^;]+<br>Duration =<br>  [0-9]+([.][0-9]+)? “s”?<br>  | [.][0-9]+ “s”?<br><br>Voice =<br>  “Astrid” |  “Brian” | “Carla” | “Carmen” |  “Celine” |<br>  “Chantal” | “Conchita” |  “Cristiano” | “Dora” |  “Emma” |<br>  “Enrique” | “Ewa” | “Filiz” | “Geraint” | “Giorgio” |<br>  “Gwyneth” | “Hans” |  “Ines” |  “Ivy” | “Jacek” |<br>  “Jan” | “Joanna” |  “Joey” |  “Justin” |  “Karl” |<br>  “Kendra” |  “Kimberly” |  “Liv” | “Lotte” | “Mads” |<br>  “Maja” |  “Marlene” | “Mathieu” | “Matthew” | “Maxim” |<br>  “Miguel” |  “Mizuki” |  “Naja” |  “Nicole” |  “Penelope” |<br>  “Raveena” | “Ricardo” | “Ruben” | “Russell” | “Tatyana” |<br>  “Salli” | “Vicki” | “Vitoria”<br>

REST API

Our API is documented using OpenAPI and published on Swagger Hub. You can learn more or try it out there.

Read API Docs

Client Libraries

If your Alexa skill uses the Alexa SDK for Node.JS, or your Google Action uses the Actions on Google SDK for Node.JS, you can start using Talestreamer in 4 steps that take about 3 minutes!

Get started with:
Alexa SDK Actions on Google SDK

If you use a different SDK, contact us to request support, or use the REST API.

FAQ

How do I use SSML with Talestreamer?
You can put an SSML speak tag in any span or stream tag.

<br><stream xmlns="http://talestreamer.ai/schema/tsml" style="volume-profile: prenormalized"><br>  <speak xmlns="http://www.w3.org/2001/10/synthesis"><br>    You say, <phoneme alphabet="ipa" ph="pɪˈkɑːn">pecan</phoneme>.<br>    I say, <phoneme alphabet="ipa" ph="ˈpi.kæn">pecan</phoneme>.<br>  </speak><br></stream><br>

Where can I get sounds that work with Talestreamer?

Sound Dogs
fmod.io
Partners in Rhyme Loops. (Great for backgrounds.)
Partners in Rhyme.
FreeSounds
Sound Bible
Public Domain Info Project
We make many of our own sounds. If you need a custom logo, voice, effect, background, or music, contact us.

Talestreamer Documentation

Table of Contents

What Talestreamer Can Do

Voice Styling

Incorporating Human Voices and Sound Effects

Background Sound and Music

Composing a Response

Separating Style From Content

Advanced Topics

Integration

Alternative Integration Approach – Using Files

One-Time Setup

Audio Upload

Examples

Side By Side Comparison of Talestreamer and Plain Text To Speech

Side By Side Comparison, With an External Stylesheet

Comparing Amazon Polly and Google Cloud Text To Speech Voices

A Scene from The Haunted Lighthouse (A Story from The Magic Door)

A Cave, With Sound Effects and Voices

A Skit, Featuring Matthew, With Background From PartnersInRhyme.com

Reference

Talestreamer Markup Language (TSML)

Talestreamer Stylesheets (TSSS)

REST API

Client Libraries

FAQ

Table of Contents

What Talestreamer Can Do

Voice Styling

Incorporating Human Voices and Sound Effects

Background Sound and Music

Composing a Response

Separating Style From Content

Advanced Topics

Integration

Alternative Integration Approach – Using Files

One-Time Setup

Audio Upload

Examples

Side By Side Comparison of Talestreamer and Plain Text To Speech

Side By Side Comparison, With an External Stylesheet

Comparing Amazon Polly and Google Cloud Text To Speech Voices

A Scene from The Haunted Lighthouse (A Story from The Magic Door)

Reserving a Ride in a Ride Sharing Skill

A Cave, With Sound Effects and Voices

A Skit, Featuring Matthew, With Background From PartnersInRhyme.com

Reference

Talestreamer Markup Language (TSML)

Talestreamer Stylesheets (TSSS)

REST API

Client Libraries

FAQ