Text-to-Speech

Twilio synthesizes speech from your text in real time and speaks the speech in any call. You can use TTS in TwiML and Twilio Studio.

1
<Response>
2
  <Say>Hello world!</Say>
3
</Response>

1
<Response>
2
  <Say language="en-US" voice="Polly.Joanna">Hello. I am Joanna and I speak American English!</Say>
3
</Response>

You can choose from four types of Twilio Text-to-Speech: Basic, Standard, Neural and Generative. These types differ in their support of technologies, languages, locales, and quality of conversation.

These voices help you learn Text-to-Speech capabilities using <Say>. Don't use these voices for production apps. These voices lack enough human-like qualities for voice call conversation. Due to their limited purpose, these voices support few languages. Twilio provides these voices at no additional cost.

These voices use standard technology in synthesized speech. They produce natural-sounding lifelike voices but might have limited human speech patterns and inflections. These voices speak using Amazon Polly and Google Standard voices.

These voices use enhanced technology in synthesized speech. They produce higher-quality and more natural-sounding voices than Standard voices. These voices speak using Amazon Polly Neural and Google WaveNet and Neural2 voices.

These voices use the generative AI technology. They produce human-like voices with apparent emotional engagement and context awareness. These voices interpret the text-input and adjust their speech. These synthetic voices sound like human voices. This makes these voices the best option for Conversational AI apps and Virtual Agents. These voices speak using Amazon Polly Generative and Google Chirp3-HD voices.

Twilio supports a large range of languages and locale variants.

The format of the voice attribute depends on the TwiML verb as shown in the following table:

The following table lists all voices available for each language and locale.

The preceding table identifies bilingual voices with (*) in the Voice column. Only Amazon Polly supports this for a limited number of voices. To learn more about the bilingual voices, see the Amazon Polly documentation.

To test the different voices, go to the Text-to-Speech page in the Twilio Console.

To define the default voice and language for your account, go to the Text-to-Speech page in the Twilio Console.

• When you don't set language or voice attributes in your <Say> TwiML verb, it uses the default values.
• When you select Default in Studio, it uses the default values.

1
<Response>
2
  <Say>Hello. I am a man!</Say>
3
</Response>

Twilio updates the offered Text-to-Speech voices on a regular basis. To access the latest voices without needing to review and change your code, use the Language Mapping feature. Your app only needs the language and the text. Twilio selects and uses the corresponding voice. Update these at any time from the Twilio Console. On the Text-to-Speech page in the Twilio Console, you can set a voice for every locale.

To set a voice for a locale, complete the following steps.

1. Go to the Text-to-Speech page in the Twilio Console.
2. Under the Current Language Mapping heading, choose the language and locale you wish to configure.
   In this example, choose English (British) (en-GB). The Test & Configure Voices By Language modal displays.
3. From the dropdown menus, select the Provider and Voice you wish to use.
   In this example, choose Amazon Polly and Emma.
4. Click Save.
5. Repeat these steps for other language and voice pairing you want to use.

With these mappings set, you can specify the language without specifying the voice when using the <Say> TwiML verb in your app.

1
<Response>
2
  <Say language="en-GB">Hello. I am Emma!</Say>
3
</Response>

To override default voice settings configured in the Twilio Console, change the <Say> voice attribute.

1
<Response>
2
  <Say voice="Polly.Joanna">Hello. I am Joanna!</Say>
3
</Response>

To override a Language Mapping's defaults, add the voice attribute.

1
<Response>
2
  <Say language="en-GB" voice="Polly.Joanna">Hello. I am Joanna!</Say>
3
</Response>

To override any default language settings configured in the Twilio Console, use the <Say> verb language attribute.

1
<Response>
2
  <Say language="de-DE">Hallo. Ich spreche Deutsch!</Say>
3
</Response>

To fine-tune synthesized speech, use Speech Synthesis Markup Language (SSML) tags. With SSML, you can specify where pauses should be, provide pronunciations for acronyms, abbreviations, dates and times, and increase or decrease the speed of spoken text. Basic voices don't support SSML.

Twilio supports a subset of SSML tags in TwiML.

SSML support might differ between Text-to-Speech providers, be limited to specific voices, or both. Review the provider-specific SSML documentation and test your app. Use of SSML tags that a Text-to-Speech provider or voice doesn't support might result in error and fail the <Say> instruction.

The following table lists the SSML tags that Twilio supports. To learn about the use of specific SSML tags, see the provider-specific documentation.

To control the volume, rate, and pitch of synthesized speech, use the SSML <prosody> tag.

1
<Response>
2
  <Say voice="Polly.Joanna">
3
    Prosody can be used to change the way words sound. The following words are
4
    <prosody volume="x-loud"> quite a bit louder than the rest of this passage.
5
    </prosody> Each morning when I wake up, <prosody rate="x-slow">I speak slowly and
6
    deliberately until I have my coffee.</prosody> I can also change the pitch of my voice
7
    using prosody. Do you like <prosody pitch="+5%"> speech with a pitch higher,</prosody>
8
    or <prosody pitch="-10%"> is a lower pitch preferable?</prosody>
9
  </Say>
10
</Response>

To choose how to pronounce a specific category of text, use the SSML <say-as> tag. This ensures that speech pronounces certain text as expected. Without <say-as>, the voice pronounces a phone number like a number.

1
<Response>
2
  <Say voice="Polly.Joanna">
3
     John's phone number is, <say-as interpret-as="telephone">4155551212</say-as>
4
  </Say>
5
</Response>

To generate TwiML with SSML within the <Say> verb, use a Twilio SDK: C#, Go, Java, Node.js, PHP, Python, or Ruby.

This SDK code generates the TwiML with SSML.

1
const VoiceResponse = require('twilio').twiml.VoiceResponse;
2

3
const response = new VoiceResponse();
4
const say = response.say(
5
  {
6
    voice: 'Polly.Joanna',
7
  },
8
  'Hi'
9
);
10
say.break({
11
  strength: 'x-weak',
12
  time: '100ms',
13
});
14
say.emphasis(
15
  {
16
    level: 'moderate',
17
  },
18
  'Words to emphasize'
19
);
20
say.p('Words to speak');
21
say.addText('aaaaaa');
22
say.phoneme(
23
  {
24
    alphabet: 'x-sampa',
25
    ph: 'pɪˈkɑːn',
26
  },
27
  'Words to speak'
28
);
29
say.addText('bbbbbbb');
30
say.prosody(
31
  {
32
    pitch: '-10%',
33
    rate: '85%',
34
    volume: '-6dB',
35
  },
36
  'Words to speak'
37
);
38
say.s('Words to speak');
39
say.sayAs(
40
  {
41
    'interpret-as': 'spell-out',
42
    role: 'yyyymmdd',
43
  },
44
  'Words to speak'
45
);
46
say.sub(
47
  {
48
    alias: 'alias',
49
  },
50
  'Words to be substituted'
51
);
52
say.w('Words to speak');
53

54
console.log(response.toString());

1
<Response>
2
  <Say voice="Polly.Joanna">
3
    Hi
4
    <break strength="x-weak" time="100ms"/>
5
    <emphasis level="moderate">Words to emphasize</emphasis>
6
    <p>Words to speak</p>
7
    aaaaaa
8
    <phoneme alphabet="x-sampa" ph="pɪˈkɑːn">Words to speak</phoneme>
9
    bbbbbbb
10
    <prosody pitch="-10%" rate="85%" volume="-6dB">Words to speak</prosody>
11
    <s>Words to speak</s>
12
    <say-as interpret-as="spell-out">Words to speak</say-as>
13
    <sub alias="alias">Words to be substituted</sub>
14
    <w>Words to speak</w>
15
  </Say>
16
</Response>

• Basic voices can process no more than 4,000 characters.
• Basic voices don't support SSML tags.

• <Say> can't process more than 3,000 characters excluding the SSML tags.
• <Say> doesn't support Amazon-specific SSML tags. These would include <amazon:auto-breath> or <amazon:effect>.
• <Say> doesn't support lexicons.
• SSML support might vary between Polly and Polly Neural voices.
  To review any differences, see the Amazon Polly SSML documentation.

• <Say> can process no more than 5,000 characters, including SSML, newlines and spaces.
• As Google includes SSML tags, newlines and spaces in the total character count, they count toward Google billing totals.
• <Say> doesn't support Google-specific SSML tags. This includes <par> or <seq>.
• SSML support may vary between Standard, WaveNet and Neural2 voices.
  To review any differences, consult the [Google SSML documentation][].

Basic voices are free of charge. For Standard, Neural, and Generative voice pricing, see Voice pricing. Twilio rounds usage towards the end of call and prices it in blocks of 100 characters. The minimum charge covers 100 characters.