Conference Campaign Solo Rich Messaging

Voice Gateway


TTS: Convert text to lifelike speech.

TTS Demo

Voice Gateway : Text-to-Speech

People like talking and listening to other people. With Text-to-Speech you can synthesise human speech and make interaction with an automated system more natural. Automating interaction with a system, which becomes desirable when it's more natural, allows you to make the system more scalable and cost-effective.

The Text-to-Speech service allows an application to have a text-to-speech (TTS) conversion performed on a long or short text. The resulting lifelike voice stream can then be delivered via a number of different channels:

  • Returned during RESTful Voice API call (synchronous)
  • HTTPS retrieval using RESTful Voice API call (asynchronous)
  • Attachment in an email or HTTPS callback (POST)
  • URL link in an email, SMS or HTTPS callback
  • Playback during a SIP call
  • Voice messaging - delivery via voice call

Find us on Zapier. Use our invite link to access Melrose Labs Speech.

Zapier: Melrose Labs Speech

Text-to-Speech is a cloud service that quickly converts text into high quality lifelike speech. You can use Text-to-Speech to develop applications that increase engagement and accessibility. Text-to-Speech supports multiple languages and includes a variety of lifelike voices, so you can build speech-enabled applications that work in multiple geographic locations and use the ideal voice for your customers.

Standard and Neural TTS

The standard speech engine produces high quality speech for all supported voices. For en-GB, en-US and some es-US and pt-BR voices, the neural speech engine can used to produce perfectly natural speech. Where a voice is supported by the neural speech engine, the service will use the neural speech engine by default.

Using the Service

The Melrose Labs Text-to-Speech service is available using the SMTP API (email), Text-to-Speech REST API and Zapier (Melrose Labs Speech).

The following languages and voices are available using the Text-to-Speech service of the Voice API:

Language Voice Sample Email (example)
Arabic (arb)Zeina (f)
Chinese, Mandarin (cmn-CN)Zhiyu (f)
Danish (da-dk)Mads (m)
Naja (f)
Dutch (nl-nl)Lotte (f)
Ruben (m)
English, Australian (en-AU)Russell (m)
Nicole (f)
English (en-GB)²Emma (f)
Amy (f)
Brian (m)
English, Indian (en-IN)Aditi (f)
Raveena (f)
English (en-US)²Salli (f)¹
Ivy (f)
Joanna (f)
Kendra (f)
Kimberly (f)
Joey (m)
Justin (m)
Matthew (m)
English, Welsh (en-GB-WLS)Geraint (m)
French (fr-FR)Céline/Celine (f)
Léa/Lea (f)
Mathieu (m)
French, Canadian (fr-CA)Chantal (f)
Germany (de-DE)Vicki (f)
Marlene (f)
Hans (m)
Hindi (hi-IN)Aditi (f)
Icelandic (is-IS)Karl (m)
Dóra/Dora (f)
Italian (it-IT)Bianca (f)
Carla (f)
Giorgio (m)
Japanese (ja-JP)Mizuki (f)
Takumi (m)
Korean (ko-KR)Seoyeon (f)
Norwegian (nb-NO)Liv (f)
Polish (pl-PL)Jan (m)
Ewa (f)
Maja (f)
Jacek (m)
Portuguese (pt-BR)Camila² (f)
Vitória/Vitoria (f)
Ricardo (m)
Portuguese (pt-PT)Cristiano (m)
Inês/Ines (f)
Romanian (ro-RO)Carmen (f)
Russian (ru-RU)Tatyana (f)
Maxim (m)
Spanish (es-ES)Enrique (m)
Lucia (f)
Conchita (f)
Spanish (es-MX)Mia (f)
Spanish (es-US)Lupe² (f)
Penélope/Penelope (f)
Miguel (m)
Swedish (sv-SE)Astrid (f)
Turkish (tr-TR)Filiz (f)
Welsh (cy-GB)Gwyneth (f)

¹ Default voice. Used for or when no voice is specified during a Voice API REST call.
² Will use neural engine unless standard engine is requested.

Using Email to Access the Text-to-Speech Service

Email can be used to easily and quickly perform a text-to-speech (TTS) conversion as an alternative to using REST HTTPS calls to the Voice API. Send an email to the Text-to-Speech service at and use the subject field to contain the text you wish converted. After a number of seconds, you will receive an email back from the service with an MP3 file containing the converted speech.

Various voices and corresponding languages are available using email addresses specific to each voice. The format of each email address is and the options for voice and language are shown in the list of available languages and voices.

An API key is currently not required when using email.

The Melrose Labs Text-to-Speech service is available using our REST API:

Convert text to speech using the Voice Gateway Text-to-Speech service with RESTful Voice API
Example using cURL

Submit conversion request and receive resulting speech


curl -X POST \
    -H 'Content-Type: application/json' \ 
    -H 'x-api-key: [API_KEY]' \ 
    -d '{"voiceText": "Welcome Allan. The event for today will begin at 9.30am in room H32.", "voice": "Emma"}' \
    --output out.mp3


MP3 file

Submit conversion request


curl -X POST \
    -H 'Content-Type: application/json' \
    -H 'x-api-key: [API_KEY]' \
    -d '{"voiceText": "Welcome Allan. The event for today will begin at 9.30am in room H32.", "voice": "Emma"}'


{"transactionID": "1ccead78-6550-4aac-a6b4-a4942b908659"}

Retrieve resulting speech


curl -X GET "" \
    -H 'x-api-key: [API_KEY]'


MP3 file

TTS Conversion Speed

Text-to-Speech Conversion Timings

The following timings were performed using synchronous API calls with cURL and an extract from Alice in Wonderland by Lewis Carol.

Number of words:15 words57 words112 words253 words
Total TTS Duration (seconds):0.5360.7150.9401.420

The Text-to-Speech service is one of the many building blocks we are releasing over the coming months as part of the Voice Gateway, and making available through the Voice API.

Need to convert speech-to-text? See our Speech-to-Text service.

Follow us on LinkedIn for updates on Melrose Labs Text-to-Speech and our other services.

Service snapshot

  • Lifelike voices
  • Asyncronous and syncronous RESTful API
  • Large selection of voices
  • Multi-language support

Find out more...

Please provide your first name.
Please provide your last name.
Please provide a valid company name.
Please provide a valid email address.
Please type your message.