Activate and configure a third-party TTS provider integration

AI-generated summary

Genesys Cloud enables configuration of third-party text-to-speech (TTS) provider integrations through the Genesys TTS Connector, allowing organizations to standardize audio output to PCM format at 8kHz while supporting multiple providers including Acapela Cloud, Cartesia, Deepgram, ElevenLabs, Emotech, ReadSpeaker, and SESTEK. The integration process requires installation of the connector, configuration through dedicated tabs (Details, Configuration, Advanced, and Credentials), and activation by transitioning status from Inactive to Active. Organizations can configure up to 10 TTS Connector instances, with each requiring specification of synthesis and voice listing URIs, request methods, and attribute mappings for text, voice, language, output format, and sample rate parameters. Configuration varies by provider but consistently involves defining voice properties with language codes and gender attributes, mapping output formats to supported audio codecs (PCM, WAV, MP3), and entering provider-specific API credentials through the Credentials tab using appropriate authentication types such as OAuth or API key authentication. Advanced JSON configuration options enable customization of output format mapping, voice language mapping, and synthesis body parameters to accommodate provider-specific requirements. Voice lists are cached upon initial activation and require a minimum 30-minute interval between disabling and re-enabling the connector to refresh available voices from the provider account. The connector has specific limitations: it does not support audio payloads in JSON bodies or SSML formatting, does not support Google Chirp 3 or Microsoft Azure TTS voices, and implements different audio streaming behaviors between call flows and bot flows. Call flows begin audio streaming immediately upon receiving provider audio, while bot flows wait for complete audio payload receipt before playback, resulting in additional latency for bot implementations. An optional PCI compliance designation is available for each integration, enabling use in secure flows at user discretion. When enabled, this designation indicates the third-party provider meets PCI DSS standards; however, use within secure flows when this option is selected is undertaken at the customer's own risk and responsibility. This comprehensive integration framework allows organizations to leverage their preferred TTS providers while maintaining standardized audio output and security considerations within Genesys Cloud workflows.

You can configure the Genesys TTS Connector integration in Genesys Cloud to use your preferred third-party text-to-speech (TTS) provider. To integrate with a third-party TTS provider, you must set the integration properties, attributes, and credentials that are required to access their API endpoint.

Notes:

You can configure up to 10 Genesys TTS Connector integration instances for an organization.
TTS audio plays as PCM and 8kHz regardless of the formats the TTS provider supports.
Genesys TTS Connector does not support audio payload in the JSON body (Google TTS voices) or SSML (Microsoft Azure custom voices). TTS Connector supports only audio streams.
Genesys TTS Connector does not support the following voices:
- Google Chirp 3 TTS voices
- Microsoft Azure TTS voices
Genesys TTS Connector displays all languages available for the configured third-party provider account. The TTS Connector caches the voice lists when it is first activated. If you add new voices to the provider account, disable the TTS Connector integration and enable it again after at least 30 minutes to refresh the list of available third-party voices.

Refer to the following sample configuration for each third-party TTS provider that Genesys Cloud currently supports:

Note: Genesys has validated these providers through testing. Genesys recommends using shorter TTS text to minimize latency. Call flows begin audio streaming immediately upon receiving audio from the provider. Bot flows do not support audio streaming and instead wait for the entire audio payload to be received before playback. Consequently, additional delays can be expected when using bot flows.

Acapela CloudClick to expand

Open the Genesys TTS Connector integration:
- If you did not previously install the integration into your Genesys Cloud organization, install the Genesys TTS Connector now.
- If you installed the integration, follow these steps to open the integration:
  1. Click Admin.
  2. Under Integrations, click Integrations.
  3. Click Menu > IT and Integrations > Integrations.
  4. Search for and open the Genesys TTS Connector integration.
In the Details tab, Genesys highly recommends that you enter a unique name for the integration that you want to configure. For example, “Genesys TTS Connector – Acapela Cloud”.
On the Genesys TTS Connector – Acapela Cloud integration page, click the Configuration tab.

Under Properties, enter the following values:

Property name	Value
Synthesize Text URI	https://acapela-cloud.com/api/command/
List Voices URI	https://acapela-cloud.com/api/account/
Synthesize Text Request Method	get
Synthesize Text Attribute	text
Synthesize Voice Attribute	voice
Synthesize Language Attribute	language
Synthesize OutputFormat Attribute	type
Synthesize Sample Rate Attribute	samplerate
Voices Attribute	voices
Voice Name Attribute	name
Voice Language Attribute	language
Voice Gender Attribute	gender
Voice Type Attribute	type

(Optional) Under Properties, select whether the third-party TTS provider is PCI compliant from the PCI Compliant list. The default value is False.
Note: The third-party TTS integration is available to use in secure flows if you select True from the PCI Compliant list. However, if you choose to set this option to True, any use within secure flows is undertaken at your own risk. For more information, see PCI DSS customer responsibility matrix.

Click the Advanced tab. Enter any additional configuration in the JSON format.
Use the following sample configuration for Acapela Cloud:

{
  "voiceMapping": {
    "languageMapping": {
      "en-AE": "arabicenglish",
      "en-AU": "australianenglish",
      "en-us": "USEnglish",
      "ar-001": "arabic"
    },
    "genderMapping": {
      "female": "1",
      "male": "2"
    }
  },
  "outputFormatMapping": {
    "audio/L16": {
      "*": "wav"
    },
    "audio/mpeg": {
      "*": "mp3"
    }
  }
}

Click the Credentials tab.
1. Click Configure. The Configure Credentials dialog box opens.
2. Select the credential type, User Defined (OAuth).
3. Click Add Credential Field, then add the following field names and values:
  Field name Value
  loginUrl https://www.acapela-cloud.com/api/login/
  email <Your email address>
  password <Your password>
4. Click OK.
Click Save.
To activate the Genesys TTS Connector integration, in the Status column click Inactive. The Change Status dialog box opens.
Click Yes. The integration’s status changes to Active.

Field name	Value
loginUrl	`https://www.acapela-cloud.com/api/login/`
email	<Your email address>
password	<Your password>

CartesiaClick to expand

Open the Genesys TTS Connector integration:
- If you did not previously install the integration into your Genesys Cloud organization, install the Genesys TTS Connector now.
- If you installed the integration, follow these steps to open the integration:
  1. Click Admin.
  2. Under Integrations, click Integrations.
  3. Click Menu > IT and Integrations > Integrations.
  4. Search for and open the Genesys TTS Connector integration.
In the Details tab, Genesys highly recommends that you enter a unique name for the integration that you want to configure. For example, “Genesys TTS Connector – Cartesia.”
On the Genesys TTS Connector – Cartesia integration page, click the Configuration tab.

Under Properties, enter the following values:

Property name	Value
Synthesize Text URI	https://api.cartesia.ai/tts/bytes
List Voices URI	https://api.cartesia.ai/voices/export
Synthesize Text Request Method	post
Synthesize Text Attribute	text
Synthesize Voice Attribute	voice
Synthesize Languages Attribute	language
Synthesize OutputFormat Attribute	audioformat
Synthesize Sample Rate Attribute	samplerate
Voices Attribute	data
Voice Id Attribute	id
Voice Name Attribute	name
Voice Language Attribute	language
Voice Gender Attribute	gender
Voice Type Attribute	type

(Optional) Under Properties, select whether the third-party TTS provider is PCI compliant from the PCI Compliant list. The default value is False.
Note: The third-party TTS integration is available to use in secure flows if you select True from the PCI Compliant list. However, if you choose to set this option to True, any use within secure flows is undertaken at your own risk. For more information, see PCI DSS customer responsibility matrix.

Click the Advanced tab. Enter any additional configuration in the JSON format.
Use the following sample configuration for Cartesia:

{
  "synthesizeBody": {
    "voice": {
      "mode": "id",
      "id": "$voice"
    },
    "model_id": "sonic-3.5",
    "transcript": "$text",
    "output_format": {
      "container": "raw",
      "encoding": "pcm_s16le",
      "sample_rate": 8000
    }
  }
}

Click the Credentials tab.
1. Click Configure. The Configure Credentials dialog box opens.
2. Select the credential type, User Defined.
3. Click Add Credential Field, then add the following field name and value:
  Field name Value
  X-API-Key <Your API key>
  Cartesia-Version <The Cartesia version in the YYYY-MM-DD format>
4. Click OK.
Click Save.
To activate the Genesys TTS Connector integration, in the Status column click Inactive. The Change Status dialog box opens.
Click Yes. The integration’s status changes to Active.

Field name	Value
X-API-Key	<Your API key>
Cartesia-Version	<The Cartesia version in the YYYY-MM-DD format>

DeepgramClick to expand

Note: As of July 2025, Deepgram does not support SSML tags.

Open the Genesys TTS Connector integration:
- If you did not previously install the integration into your Genesys Cloud organization, install the Genesys TTS Connector now.
- If you installed the integration, follow these steps to open the integration:
  1. Click Admin.
  2. Under Integrations, click Integrations.
  3. Click Menu > IT and Integrations > Integrations.
  4. Search for and open the Genesys TTS Connector integration.
In the Details tab, Genesys highly recommends that you enter a unique name for the integration that you want to configure. For example, “Genesys TTS Connector – Deepgram.”
On the Genesys TTS Connector – Deepgram integration page, click the Configuration tab.

Under Properties, enter the following values:

Property name	Value
Synthesize Text URI	https://api.deepgram.com/v1/speak
List Voices URI	https://api.deepgram.com/v1/models
Synthesize Text Request Method	post
Synthesize Text Attribute	text
Synthesize Voice Attribute	model
Synthesize Language Attribute	language
Synthesize OutputFormat Attribute	encoding
Synthesize Sample Rate Attribute	sample_rate
Voices Attribute	tts
Voice Name Attribute	canonical_name
Voice Language Attribute	languages
Voice Gender Attribute	gender
Voice Type Attribute	type

(Optional) Under Properties, select whether the third-party TTS provider is PCI compliant from the PCI Compliant list. The default value is False.
Note: The third-party TTS integration is available to use in secure flows if you select True from the PCI Compliant list. However, if you choose to set this option to True, any use within secure flows is undertaken at your own risk. For more information, see PCI DSS customer responsibility matrix.

Click the Advanced tab. Enter any additional configuration in the JSON format.
Use the following sample configuration for Deepgram:

{
  "outputFormatMapping": {
    "audio/L16": {
      "*": "linear16"
    }
  },
  "voiceMapping": {
    "languageMapping": {
      "en-us": "en"
    }
  },
  "synthesizeBody": {
    "text": "$text"
  }
}

Click the Credentials tab.
1. Click Configure. The Configure Credentials dialog box opens.
2. Select the credential type, User Defined.
3. Click Add Credential Field, then add the following field name and value:
  Field name Value
  Authorization Token <Your Deepgram API key>
4. Click OK.
Click Save.
To activate the Genesys TTS Connector integration, in the Status column click Inactive. The Change Status dialog box opens.
Click Yes. The integration’s status changes to Active.

Field name	Value
Authorization	Token <Your Deepgram API key>

ElevenLabsClick to expand

Open the Genesys TTS Connector integration:
- If you did not previously install the integration into your Genesys Cloud organization, install the Genesys TTS Connector now.
- If you installed the integration, follow these steps to open the integration:
  1. Click Admin.
  2. Under Integrations, click Integrations.
  3. Click Menu > IT and Integrations > Integrations.
  4. Search for and open the Genesys TTS Connector integration.
In the Details tab, Genesys highly recommends that you enter a unique name for the integration that you want to configure. For example, “Genesys TTS Connector – ElevenLabs.”
On the Genesys TTS Connector – ElevenLabs integration page, click the Configuration tab.

Under Properties, enter the following values:

Property name	Value
Synthesize Text URI	https://api.elevenlabs.io/v1/text-to-speech/$voice/stream
List Voices URI	https://api.elevenlabs.io/v2/voices?page_size=100
Synthesize Text Request Method	post
Synthesize Text Attribute
Synthesize Voice Attribute
Synthesize Languages Attribute
Synthesize OutputFormat Attribute	output_format
Synthesize Sample Rate Attribute	samplerate
Voices Attribute	voices
Voice Id Attribute	voice_id
Voice Name Attribute	name
Voice Language Attribute	fine_tuning\|language
Voice Gender Attribute	labels\|gender
Voice Type Attribute	type

(Optional) Under Properties, select whether the third-party TTS provider is PCI compliant from the PCI Compliant list. The default value is False.
Note: The third-party TTS integration is available to use in secure flows if you select True from the PCI Compliant list. However, if you choose to set this option to True, any use within secure flows is undertaken at your own risk. For more information, see PCI DSS customer responsibility matrix.

Click the Advanced tab. Enter any additional configuration in the JSON format.
Use the following sample configuration for ElevenLabs:

{
  "outputFormatMapping": {
    "audio/L16": { 
	"8000": "pcm_8000",
        "16000": "pcm_16000"
    }
  },
  "voiceMapping": {
    "languageMapping": {
      "en-us": "en"
    }
  },
  "synthesizeBody": {
    "apply_text_normalization": "on",
    "text": "$text",
    "model_id": "eleven_flash_v2_5"
  }
}

Click the Credentials tab.
1. Click Configure. The Configure Credentials dialog box opens.
2. Select the credential type, User Defined.
3. Click Add Credential Field, then add the following field name and value:
  Field name Value
  xi-api-key <Your ElevenLabs API key>
4. Click OK.
Click Save.
To activate the Genesys TTS Connector integration, in the Status column click Inactive. The Change Status dialog box opens.
Click Yes. The integration’s status changes to Active.

Field name	Value
xi-api-key	<Your ElevenLabs API key>

Emotech Click to expand

Open the Genesys TTS Connector integration:
- If you did not previously install the integration into your Genesys Cloud organization, install the Genesys TTS Connector now.
- If you installed the integration, follow these steps to open the integration:
  1. Click Admin.
  2. Under Integrations, click Integrations.
  3. Click Menu > IT and Integrations > Integrations.
  4. Search for and open the Genesys TTS Connector integration.
In the Details tab, Genesys highly recommends that you enter a unique name for the integration that you want to configure. For example, “Genesys TTS Connector – Emotech.”
On the Genesys TTS Connector – Emotech integration page, click the Configuration tab.

Under Properties, enter the following values:

Property name	Value
Synthesize Text URI	https://speech-synthesis-dev.api.emotechlab.com/v2/synthesize
List Voices URI	https://speech-synthesis-dev.api.emotechlab.com/v2/voices
Synthesize Text Request Method	get
Synthesize Text Attribute	text
Synthesize Voice Attribute	voice
Synthesize Language Attribute	language
Synthesize OutputFormat Attribute	audioformat
Synthesize Sample Rate Attribute	samplerate
Voices Attribute	voices
Voice Name Attribute	name
Voice Language Attribute	language
Voice Gender Attribute	gender
Voice Type Attribute	type

(Optional) Under Properties, select whether the third-party TTS provider is PCI compliant from the PCI Compliant list. The default value is False.
Note: The third-party TTS integration is available to use in secure flows if you select True from the PCI Compliant list. However, if you choose to set this option to True, any use within secure flows is undertaken at your own risk. For more information, see PCI DSS customer responsibility matrix.

Click the Advanced tab. Enter any additional configuration in the JSON format.
Use the following sample configuration for Emotech:

{
  "voices": [
    {
      "name": "ar-SA_Female_1",
      "gender": "female",
      "language": "ar-SA"
    },
    {
      "name": "ar-SA_Male_1",
      "gender": "male",
      "language": "ar-SA"
    },
    {
      "name": "ar-SA_Male_2",
      "gender": "male",
      "language": "ar-SA"
    },
    {
      "name": "en-US_Female_1",
      "gender": "female",
      "language": "en-US"
    },
    {
      "gender": "male",
      "name": "ar-EG_Male_1",
      "language": "ar-EG"
    },
    {
      "gender": "female",
      "name": "ar-EG_Female_1",
      "language": "ar-EG"
    }
  ],
  "voiceMapping": {
    "languageMapping": {
      "ar-sa": "ar-SA",
      "ar-ae": "ar-EG",
      "en-us": "en-US"
    }
  },
  "outputFormatMapping": {
    "audio/L16": {
      "*": "wav"
    },
    "audio/mpeg": {
      "*": "mp3"
    }
  }
}

Click the Credentials tab.
1. Click Configure. The Configure Credentials dialog box opens.
2. Select the credential type, ttsConnectorUserDefinedPathAuth.
3. Type apikey in the Path Credential Name field.
4. Enter your API key in the Path Credential field.
5. Click OK.
Click Save.
To activate the Genesys TTS Connector integration, in the Status column click Inactive. The Change Status dialog box opens.
Click Yes. The integration’s status changes to Active.

ReadSpeakerClick to expand

Open the Genesys TTS Connector integration:
- If you did not previously install the integration into your Genesys Cloud organization, install the Genesys TTS Connector now.
- If you installed the integration, follow these steps to open the integration:
  1. Click Admin.
  2. Under Integrations, click Integrations.
  3. Click Menu > IT and Integrations > Integrations.
  4. Search for and open the Genesys TTS Connector integration.
In the Details tab, Genesys highly recommends that you enter a unique name for the integration that you want to configure. For example, “Genesys TTS Connector – ReadSpeaker.”
On the Genesys TTS Connector – ReadSpeaker integration page, click the Configuration tab.

Under Properties, enter the following values:

Property name	Value
Synthesize Text URI	https://scapi-eu.readspeaker.com/a/speak?container=none&streaming=0
List Voices URI	https://scapi-eu.readspeaker.com/a/speak?command=voiceinfo
Synthesize Text Request Method	get
Synthesize Text Attribute	text
Synthesize Voice Attribute	voice
Synthesize Language Attribute	lang
Synthesize OutputFormat Attribute	audioformat
Synthesize Sample Rate Attribute	samplerate
Voices Attribute	speakers
Voice Name Attribute	voice
Voice Language Attribute	language
Voice Gender Attribute	gender
Voice Type Attribute	type

(Optional) Under Properties, select whether the third-party TTS provider is PCI compliant from the PCI Compliant list. The default value is False.
Note: The third-party TTS integration is available to use in secure flows if you select True from the PCI Compliant list. However, if you choose to set this option to True, any use within secure flows is undertaken at your own risk. For more information, see PCI DSS customer responsibility matrix.

Click the Advanced tab. Enter any additional configuration in the JSON format.
Use the following sample configuration for ReadSpeaker:

{
  "outputFormatMapping": {
    "audio/L16": {
      "8000": "pcm",
      "16000": "pcm_16_16k",
      "22050": "pcm_16_22k"
    },
    "audio/mpeg": {
      "*": "mp3"
    }
  },
  "voiceMapping": {
    "languageMapping": {
      "ja-jp": "ja_jp",
      "en-us": "en_us"
    }
  }
}

Click the Credentials tab.
1. Click Configure. The Configure Credentials dialog box opens.
2. Select the credential type, ttsConnectorUserDefinedPathAuth.
3. Type key in the Path Credential Name field.
4. Enter your API key in the Path Credential field.
5. Click OK.
Click Save.
To activate the Genesys TTS Connector integration, in the Status column click Inactive. The Change Status dialog box opens.
Click Yes. The integration’s status changes to Active.

SESTEKClick to expand

Open the Genesys TTS Connector integration:
- If you did not previously install the integration into your Genesys Cloud organization, install the Genesys TTS Connector now.
- If you installed the integration, follow these steps to open the integration:
  1. Click Menu > IT and Integrations > Integrations.
  2. Search for and open the Genesys TTS Connector integration.
In the Details tab, Genesys highly recommends that you enter a unique name for the integration that you want to configure. For example, “Genesys TTS Connector – SESTEK”.
On the Genesys TTS Connector – SESTEK integration page, click the Configuration tab.

Under Properties, enter the following values:

Property name	Value
Synthesize Text URI	https://integration.eu.knovvu.com/genesys-ttsconnector/genesysttsconnector/tts
List Voices URI	https://integration.eu.knovvu.com/genesys-ttsconnector/genesysttsconnector/voices
Synthesize Text Request Method	post
Synthesize Text Attribute	text
Synthesize Voice Attribute	voice
Synthesize Language Attribute	language
Synthesize OutputFormat Attribute	format
Synthesize Sample Rate Attribute	samplerate
Voices Attribute	voices
Voice Name Attribute	name
Voice Language Attribute	language
Voice Gender Attribute	gender
Voice Type Attribute	type

(Optional) Under Properties, select whether the third-party TTS provider is PCI compliant from the PCI Compliant list. The default value is False.
Note: The third-party TTS integration is available to use in secure flows if you select True from the PCI Compliant list. However, if you choose to set this option to True, any use within secure flows is undertaken at your own risk. For more information, see PCI DSS customer responsibility matrix.

Click the Advanced tab. Enter any additional configuration in the JSON format.
Use the following sample configuration for SESTEK:

{
  "voiceMapping": {
    "languageMapping": {
      "ar-sa": "ar-SA",
      "tr-tr": "tr-TR",
      "en-us": "en-US"
    },
    "genderMapping": {
      "female": "Female",
      "male": "Male"
    }
  }
}

Click the Credentials tab.
1. Click Configure. The Configure Credentials dialog box opens.
2. Select the credential type, Basic Auth.
3. Enter your access credentials such as username and password.
4. Click Confirm.
Click Save.
To activate the Genesys TTS Connector integration, in the Status column click Inactive. The Change Status dialog box opens.
Click Yes. The integration’s status changes to Active.

[NEXT] Was this article helpful?

Get user feedback about articles.

Property name

Value

Synthesize Text URI

https://acapela-cloud.com/api/command/

List Voices URI

https://acapela-cloud.com/api/account/

Synthesize Text Request Method

get

Synthesize Text Attribute

text

Synthesize Voice Attribute

voice

Synthesize Language Attribute

language

Synthesize OutputFormat Attribute

type

Synthesize Sample Rate Attribute

samplerate

Voices Attribute

voices

Voice Name Attribute

name

Voice Language Attribute

language

Voice Gender Attribute

gender

Voice Type Attribute

type

{ "voiceMapping": { "languageMapping": { "en-AE": "arabicenglish", "en-AU": "australianenglish", "en-us": "USEnglish", "ar-001": "arabic" }, "genderMapping": { "female": "1", "male": "2" } }, "outputFormatMapping": { "audio/L16": { "*": "wav" }, "audio/mpeg": { "*": "mp3" } } }

Field name	Value
loginUrl	`https://www.acapela-cloud.com/api/login/`
email	<Your email address>
password	<Your password>

Field name

Value

loginUrl

https://www.acapela-cloud.com/api/login/

password

Property name

Value

Synthesize Text URI

https://api.cartesia.ai/tts/bytes

List Voices URI

https://api.cartesia.ai/voices/export

Synthesize Text Request Method

post

Synthesize Text Attribute

text

Synthesize Voice Attribute

voice

Synthesize Languages Attribute

language

Synthesize OutputFormat Attribute

audioformat

Synthesize Sample Rate Attribute

samplerate

Voices Attribute

data

Voice Id Attribute

Voice Name Attribute

name

Voice Language Attribute

language

Voice Gender Attribute

gender

Voice Type Attribute

type

{ "synthesizeBody": { "voice": { "mode": "id", "id": "$voice" }, "model_id": "sonic-3.5", "transcript": "$text", "output_format": { "container": "raw", "encoding": "pcm_s16le", "sample_rate": 8000 } } }

Field name	Value
X-API-Key	<Your API key>
Cartesia-Version	<The Cartesia version in the YYYY-MM-DD format>

Field name

Value

X-API-Key

Cartesia-Version

Property name

Value

Synthesize Text URI

https://api.deepgram.com/v1/speak

List Voices URI

https://api.deepgram.com/v1/models

Synthesize Text Request Method

post

Synthesize Text Attribute

text

Synthesize Voice Attribute

model

Synthesize Language Attribute

language

Synthesize OutputFormat Attribute

encoding

Synthesize Sample Rate Attribute

sample_rate

Voices Attribute

tts

Voice Name Attribute

canonical_name

Voice Language Attribute

languages

Voice Gender Attribute

gender

Voice Type Attribute

type

{ "outputFormatMapping": { "audio/L16": { "*": "linear16" } }, "voiceMapping": { "languageMapping": { "en-us": "en" } }, "synthesizeBody": { "text": "$text" } }

Field name	Value
Authorization	Token <Your Deepgram API key>

Field name

Value

Authorization

Token <Your Deepgram API key>

Property name

Value

Synthesize Text URI

https://api.elevenlabs.io/v1/text-to-speech/$voice/stream

List Voices URI

https://api.elevenlabs.io/v2/voices?page_size=100

Synthesize Text Request Method

post

Synthesize Text Attribute

Synthesize Voice Attribute

Synthesize Languages Attribute

Synthesize OutputFormat Attribute

output_format

Synthesize Sample Rate Attribute

samplerate

Voices Attribute

voices

Voice Id Attribute

voice_id

Voice Name Attribute

name

Voice Language Attribute

fine_tuning|language

Voice Gender Attribute

labels|gender

Voice Type Attribute

type

{ "outputFormatMapping": { "audio/L16": { "8000": "pcm_8000", "16000": "pcm_16000" } }, "voiceMapping": { "languageMapping": { "en-us": "en" } }, "synthesizeBody": { "apply_text_normalization": "on", "text": "$text", "model_id": "eleven_flash_v2_5" } }

Field name	Value
xi-api-key	<Your ElevenLabs API key>

Field name

Value

xi-api-key

Property name

Value

Synthesize Text URI

https://speech-synthesis-dev.api.emotechlab.com/v2/synthesize

List Voices URI

https://speech-synthesis-dev.api.emotechlab.com/v2/voices

Synthesize Text Request Method

get

Synthesize Text Attribute

text

Synthesize Voice Attribute

voice

Synthesize Language Attribute

language

Synthesize OutputFormat Attribute

audioformat

Synthesize Sample Rate Attribute

samplerate

Voices Attribute

voices

Voice Name Attribute

name

Voice Language Attribute

language

Voice Gender Attribute

gender

Voice Type Attribute

type

{ "voices": [ { "name": "ar-SA_Female_1", "gender": "female", "language": "ar-SA" }, { "name": "ar-SA_Male_1", "gender": "male", "language": "ar-SA" }, { "name": "ar-SA_Male_2", "gender": "male", "language": "ar-SA" }, { "name": "en-US_Female_1", "gender": "female", "language": "en-US" }, { "gender": "male", "name": "ar-EG_Male_1", "language": "ar-EG" }, { "gender": "female", "name": "ar-EG_Female_1", "language": "ar-EG" } ], "voiceMapping": { "languageMapping": { "ar-sa": "ar-SA", "ar-ae": "ar-EG", "en-us": "en-US" } }, "outputFormatMapping": { "audio/L16": { "*": "wav" }, "audio/mpeg": { "*": "mp3" } } }

Property name

Value

Synthesize Text URI

https://scapi-eu.readspeaker.com/a/speak?container=none&streaming=0

List Voices URI

https://scapi-eu.readspeaker.com/a/speak?command=voiceinfo

Synthesize Text Request Method

get

Synthesize Text Attribute

text

Synthesize Voice Attribute

voice

Synthesize Language Attribute

lang

Synthesize OutputFormat Attribute

audioformat

Synthesize Sample Rate Attribute

samplerate

Voices Attribute

speakers

Voice Name Attribute

voice

Voice Language Attribute

language

Voice Gender Attribute

gender

Voice Type Attribute

type

{ "outputFormatMapping": { "audio/L16": { "8000": "pcm", "16000": "pcm_16_16k", "22050": "pcm_16_22k" }, "audio/mpeg": { "*": "mp3" } }, "voiceMapping": { "languageMapping": { "ja-jp": "ja_jp", "en-us": "en_us" } } }

Property name

Value

Synthesize Text URI

https://integration.eu.knovvu.com/genesys-ttsconnector/genesysttsconnector/tts

List Voices URI

https://integration.eu.knovvu.com/genesys-ttsconnector/genesysttsconnector/voices

Synthesize Text Request Method

post

Synthesize Text Attribute

text

Synthesize Voice Attribute

voice

Synthesize Language Attribute

language

Synthesize OutputFormat Attribute

format

Synthesize Sample Rate Attribute

samplerate

Voices Attribute

voices

Voice Name Attribute

name

Voice Language Attribute

language

Voice Gender Attribute

gender

Voice Type Attribute

type

{ "voiceMapping": { "languageMapping": { "ar-sa": "ar-SA", "tr-tr": "tr-TR", "en-us": "en-US" }, "genderMapping": { "female": "Female", "male": "Male" } } }

Activate and configure a third-party TTS provider integration

[NEXT] Was this article helpful?

Loading...

Activate and configure a third-party TTS provider integration

[NEXT] Was this article helpful?