Voice RSS Logo
Voice RSS Home Voice RSS Contacts Voice RSS Site Map Login  

Follow VoiceRSS on LinkedIn Follow VoiceRSS on Facebook Follow VoiceRSS on Twitter  

Text-to-speech (TTS) API Documentation

The Voice RSS Text-to-Speech (TTS) API allows conversion of textual content to speech easier than ever. Just connect to our Text-to-Speech (TTS) API with a few lines of code and get verbal representation of a textual content. For converting text to speech you don’t need special hardware to care about intensive use of CPU and memory during conversion operations.

Voice RSS provides a very human-sounding voices and supports 49 languages with 100 voices. The Text-to-Speech (TTS) API supports cross-platrom use of online text-to-speech service. Voice RSS allows your application to deliver auditory information via Text-to-Speech (TTS) API without any software installation!

To get started with the Voice RSS Text-to-Speech (TTS) API please get API key. Here you'll find documentation and technical details about using Text-to-Speech (TTS) API.

You can test our Text-to-Speech (TTS) API in live demo mode.

If you have any questions or suggestions please feel free to contact us via e-mail.

The Voice RSS Text-To-Speech API creates high quality audio stream. The API doesn’t support callbacks and it synchronously returns audio data or an error message in the same request.

The Text-To-Speech API provides a very easy and simple one-line use. Just put the API key and language in the URL and you'll receive an audio data containing the specified text.


The Text-To-Speech API supports the following protocols:


URL format

The API has the following URL format:

or the following via HTTPS

Where <parameters> is list of parameters that API supports. The parameters may be provided in query string (HTTP GET) or as form parameters (HTTP POST) as well.

Example of request

The following examples demonstrat request via HTTP GET with variable parameters:

http://api.voicerss.org/?key=1234567890QWERTY&hl=en-us&src=Hello, world!
http://api.voicerss.org/?key=1234567890QWERTY&hl=en-us&v=Amy&src=Hello, world!
http://api.voicerss.org/?key=1234567890QWERTY&hl=en-us&c=MP3&src=Hello, world!
http://api.voicerss.org/?key=1234567890QWERTY&hl=en-us&c=MP3&f=16khz_16bit_stereo&src=Hello, world!

where 1234567890QWERTY is the API key under the account.


The Text-To-Speech API supports the following list of parameters. The parameters have name-value pair (NVP) format.

Parameter name Parameter requirement Parameter description
key Mandatory The API key
src Mandatory The textual content for converting to speech (length limited by 100KB).
hl Mandatory The textual content language. Allows values: see Languages.
v Optional The speech voice. Allows values: see Voices. Default value: depends on a language.
r Optional The speech rate (speed). Allows values: from -10 (slowest speed) up to 10 (fastest speed). Default value: 0 (normal speed).
c Optional The speech audio codec. Allows values: see Audio Codecs. Default value: WAV.
f Optional The speech audio formats. Allows values: see Audio Formats. Default value: 8khz_8bit_mono.
ssml Optional The SSML textual content format (see SSML documentation). Allows values: true and false. Default value: false.
b64 Optional Defines output as a Base64 string format (for an internet browser playing). Allows values: true and false. Default value: false.


The API allows convert textual content to audio format in the following languages:

Language code Language name
ar-eg Arabic (Egypt)
ar-sa Arabic (Saudi Arabia)
bg-bg Bulgarian
ca-es Catalan
zh-cn Chinese (China)
zh-hk Chinese (Hong Kong)
zh-tw Chinese (Taiwan)
hr-hr Croatian
cs-cz Czech
da-dk Danish
nl-be Dutch (Belgium)
nl-nl Dutch (Netherlands)
en-au English (Australia)
en-ca English (Canada)
en-gb English (Great Britain)
en-in English (India)
en-ie English (Ireland)
en-us English (United States)
fi-fi Finnish
fr-ca French (Canada)
fr-fr French (France)
fr-ch French (Switzerland)
de-at German (Austria)
de-de German (Germany)
de-ch German (Switzerland)
el-gr Greek
he-il Hebrew
hi-in Hindi
hu-hu Hungarian
id-id Indonesian
it-it Italian
ja-jp Japanese
ko-kr Korean
ms-my Malay
nb-no Norwegian
pl-pl Polish
pt-br Portuguese (Brazil)
pt-pt Portuguese (Portugal)
ro-ro Romanian
ru-ru Russian
sk-sk Slovak
sl-si Slovenian
es-mx Spanish (Mexico)
es-es Spanish (Spain)
sv-se Swedish
ta-in Tamil
th-th Thai
tr-tr Turkish
vi-vn Vietnamese


The API allows convert textual content to audio format with the following voices:

Language name Voice name Voice gender Default voice for a language
Arabic (Egypt) Oda Female Yes
Arabic (Saudi Arabia) Salim Male Yes
Bulgarian Dimo Male Yes
Catalan Rut Female Yes
Chinese (China) Luli Female Yes
Shu Female No
Chow Female No
Wang Male No
Chinese (Hong Kong) Jia Female Yes
Xia Female No
Chen Male No
Chinese (Taiwan) Akemi Female Yes
Lin Female No
Lee Male No
Croatian Nikola Male Yes
Czech Josef Male Yes
Danish Freja Female Yes
Dutch (Belgium) Daan Male Yes
Dutch (Netherlands) Lotte Female Yes
Bram Male No
English (Australia) Zoe Female Yes
Isla Female No
Evie Female No
Jack Male No
English (Canada) Rose Female Yes
Clara Female No
Emma Female No
Mason Male No
English (Great Britain) Alice Female Yes
Nancy Female No
Lily Female No
Harry Male No
English (India) Eka Female Yes
Jai Female No
Ajit Male No
English (Ireland) Oran Male Yes
English (United States) Linda Female Yes
Amy Female No
Mary Female No
John Male No
Mike Male No
Finnish Aada Female Yes
French (Canada) Emile Female Yes
Olivia Female No
Logan Female No
Felix Male No
French (France) Bette Female Yes
Iva Female No
Zola Female No
Axel Male No
French (Switzerland) Theo Male Yes
German (Austria) Lukas Male Yes
German (Germany) Hanna Female Yes
Lina Female No
Jonas Male No
German (Switzerland) Tim Male Yes
Greek Neo Male Yes
Hebrew Rami Male Yes
Hindi Puja Female Yes
Kabir Male No
Hungarian Mate Male Yes
Indonesian Intan Male Yes
Italian Bria Female Yes
Mia Female No
Pietro Male No
Japanese Hina Female Yes
Airi Female No
Fumi Female No
Akira Male No
Korean Nari Female Yes
Malay Aqil Male Yes
Norwegian Marte Female Yes
Erik Male No
Polish Julia Female Yes
Jan Male No
Portuguese (Brazil) Marcia Female Yes
Ligia Female No
Yara Female No
Dinis Male No
Portuguese (Portugal) Leonor Female Yes
Romanian Doru Male Yes
Russian Olga Female Yes
Marina Female No
Peter Male No
Slovak Beda Male Yes
Slovenian Vid Male Yes
Spanish (Mexico) Juana Female Yes
Silvia Female No
Teresa Female No
Jose Male No
Spanish (Spain) Camila Female Yes
Sofia Female No
Luna Female No
Diego Male No
Swedish Molly Female Yes
Hugo Male No
Tamil Sai Male Yes
Thai Ukrit Male Yes
Turkish Omer Male Yes
Vietnamese Chi Male Yes

Audio Codecs

The API allows convert textual content to audio format in the following codecs:

Audio codec

Audio Formats

The API allows convert textual content to audio format in the following formats:

Audio format code Audio format description
8khz_8bit_mono 8 kHz, 8 Bit, Mono
8khz_8bit_stereo 8 kHz, 8 Bit, Stereo
8khz_16bit_mono 8 kHz, 16 Bit, Mono
8khz_16bit_stereo 8 kHz, 16 Bit, Stereo
11khz_8bit_mono 11 kHz, 8 Bit, Mono
11khz_8bit_stereo 11 kHz, 8 Bit, Stereo
11khz_16bit_mono 11 kHz, 16 Bit, Mono
11khz_16bit_stereo 11 kHz, 16 Bit, Stereo
12khz_8bit_mono 12 kHz, 8 Bit, Mono
12khz_8bit_stereo 12 kHz, 8 Bit, Stereo
12khz_16bit_mono 12 kHz, 16 Bit, Mono
12khz_16bit_stereo 12 kHz, 16 Bit, Stereo
16khz_8bit_mono 16 kHz, 8 Bit, Mono
16khz_8bit_stereo 16 kHz, 8 Bit, Stereo
16khz_16bit_mono 16 kHz, 16 Bit, Mono
16khz_16bit_stereo 16 kHz, 16 Bit, Stereo
22khz_8bit_mono 22 kHz, 8 Bit, Mono
22khz_8bit_stereo 22 kHz, 8 Bit, Stereo
22khz_16bit_mono 22 kHz, 16 Bit, Mono
22khz_16bit_stereo 22 kHz, 16 Bit, Stereo
24khz_8bit_mono 24 kHz, 8 Bit, Mono
24khz_8bit_stereo 24 kHz, 8 Bit, Stereo
24khz_16bit_mono 24 kHz, 16 Bit, Mono
24khz_16bit_stereo 24 kHz, 16 Bit, Stereo
32khz_8bit_mono 32 kHz, 8 Bit, Mono
32khz_8bit_stereo 32 kHz, 8 Bit, Stereo
32khz_16bit_mono 32 kHz, 16 Bit, Mono
32khz_16bit_stereo 32 kHz, 16 Bit, Stereo
44khz_8bit_mono 44 kHz, 8 Bit, Mono
44khz_8bit_stereo 44 kHz, 8 Bit, Stereo
44khz_16bit_mono 44 kHz, 16 Bit, Mono
44khz_16bit_stereo 44 kHz, 16 Bit, Stereo
48khz_8bit_mono 48 kHz, 8 Bit, Mono
48khz_8bit_stereo 48 kHz, 8 Bit, Stereo
48khz_16bit_mono 48 kHz, 16 Bit, Mono
48khz_16bit_stereo 48 kHz, 16 Bit, Stereo
alaw_8khz_mono ALaw, 8 kHz, Mono
alaw_8khz_stereo ALaw, 8 kHz, Stereo
alaw_11khz_mono ALaw, 11 kHz, Mono
alaw_11khz_stereo ALaw, 11 kHz, Stereo
alaw_22khz_mono ALaw, 22 kHz, Mono
alaw_22khz_stereo ALaw, 22 kHz, Stereo
alaw_44khz_mono ALaw, 44 kHz, Mono
alaw_44khz_stereo ALaw, 44 kHz, Stereo
ulaw_8khz_mono uLaw, 8 kHz, Mono
ulaw_8khz_stereo uLaw, 8 kHz, Stereo
ulaw_11khz_mono uLaw, 11 kHz, Mono
ulaw_11khz_stereo uLaw, 11 kHz, Stereo
ulaw_22khz_mono uLaw, 22 kHz, Mono
ulaw_22khz_stereo uLaw, 22 kHz, Stereo
ulaw_44khz_mono uLaw, 44 kHz, Mono
ulaw_44khz_stereo uLaw, 44 kHz, Stereo


The Text-To-Speech API returns the following errors:

Error description
The account is inactive!
The subscription is expired or requests count limitation is exceeded!
The request content length is too large!
The language does not support!
The language is not specified!
The text is not specified!
The API key is not available!
The API key is not specified!
The subscription does not support SSML!

Each error starts with the prefix 'ERROR: '.

Example of an error message: 'ERROR: The API key is not specified!'