Cloud Text-to-Speech V1 API - Class Google::Cloud::TextToSpeech::V1::SynthesisInput (v1.12.0)

Reference documentation and code samples for the Cloud Text-to-Speech V1 API class Google::Cloud::TextToSpeech::V1::SynthesisInput.

Contains text input to be synthesized. Either text or ssml must be supplied. Supplying both or neither returns [google.rpc.Code.INVALID_ARGUMENT][google.rpc.Code.INVALID_ARGUMENT]. The input size is limited to 5000 bytes.

Inherits

  • Object

Extended By

  • Google::Protobuf::MessageExts::ClassMethods

Includes

  • Google::Protobuf::MessageExts

Methods

#custom_pronunciations

def custom_pronunciations() -> ::Google::Cloud::TextToSpeech::V1::CustomPronunciations
Returns
  • (::Google::Cloud::TextToSpeech::V1::CustomPronunciations) — Optional. The pronunciation customizations are applied to the input. If this is set, the input is synthesized using the given pronunciation customizations.

    The initial support is for en-us, with plans to expand to other locales in the future. Instant Clone voices aren't supported.

    In order to customize the pronunciation of a phrase, there must be an exact match of the phrase in the input types. If using SSML, the phrase must not be inside a phoneme tag.

#custom_pronunciations=

def custom_pronunciations=(value) -> ::Google::Cloud::TextToSpeech::V1::CustomPronunciations
Parameter
  • value (::Google::Cloud::TextToSpeech::V1::CustomPronunciations) — Optional. The pronunciation customizations are applied to the input. If this is set, the input is synthesized using the given pronunciation customizations.

    The initial support is for en-us, with plans to expand to other locales in the future. Instant Clone voices aren't supported.

    In order to customize the pronunciation of a phrase, there must be an exact match of the phrase in the input types. If using SSML, the phrase must not be inside a phoneme tag.

Returns
  • (::Google::Cloud::TextToSpeech::V1::CustomPronunciations) — Optional. The pronunciation customizations are applied to the input. If this is set, the input is synthesized using the given pronunciation customizations.

    The initial support is for en-us, with plans to expand to other locales in the future. Instant Clone voices aren't supported.

    In order to customize the pronunciation of a phrase, there must be an exact match of the phrase in the input types. If using SSML, the phrase must not be inside a phoneme tag.

#markup

def markup() -> ::String
Returns
  • (::String) — Markup for HD voices specifically. This field may not be used with any other voices.

    Note: The following fields are mutually exclusive: markup, text, ssml, multi_speaker_markup. If a field in that set is populated, all other fields in the set will automatically be cleared.

#markup=

def markup=(value) -> ::String
Parameter
  • value (::String) — Markup for HD voices specifically. This field may not be used with any other voices.

    Note: The following fields are mutually exclusive: markup, text, ssml, multi_speaker_markup. If a field in that set is populated, all other fields in the set will automatically be cleared.

Returns
  • (::String) — Markup for HD voices specifically. This field may not be used with any other voices.

    Note: The following fields are mutually exclusive: markup, text, ssml, multi_speaker_markup. If a field in that set is populated, all other fields in the set will automatically be cleared.

#multi_speaker_markup

def multi_speaker_markup() -> ::Google::Cloud::TextToSpeech::V1::MultiSpeakerMarkup
Returns
  • (::Google::Cloud::TextToSpeech::V1::MultiSpeakerMarkup) — The multi-speaker input to be synthesized. Only applicable for multi-speaker synthesis.

    Note: The following fields are mutually exclusive: multi_speaker_markup, text, markup, ssml. If a field in that set is populated, all other fields in the set will automatically be cleared.

#multi_speaker_markup=

def multi_speaker_markup=(value) -> ::Google::Cloud::TextToSpeech::V1::MultiSpeakerMarkup
Parameter
  • value (::Google::Cloud::TextToSpeech::V1::MultiSpeakerMarkup) — The multi-speaker input to be synthesized. Only applicable for multi-speaker synthesis.

    Note: The following fields are mutually exclusive: multi_speaker_markup, text, markup, ssml. If a field in that set is populated, all other fields in the set will automatically be cleared.

Returns
  • (::Google::Cloud::TextToSpeech::V1::MultiSpeakerMarkup) — The multi-speaker input to be synthesized. Only applicable for multi-speaker synthesis.

    Note: The following fields are mutually exclusive: multi_speaker_markup, text, markup, ssml. If a field in that set is populated, all other fields in the set will automatically be cleared.

#prompt

def prompt() -> ::String
Returns
  • (::String) — This system instruction is supported only for controllable/promptable voice models. If this system instruction is used, we pass the unedited text to Gemini-TTS. Otherwise, a default system instruction is used. AI Studio calls this system instruction, Style Instructions.

#prompt=

def prompt=(value) -> ::String
Parameter
  • value (::String) — This system instruction is supported only for controllable/promptable voice models. If this system instruction is used, we pass the unedited text to Gemini-TTS. Otherwise, a default system instruction is used. AI Studio calls this system instruction, Style Instructions.
Returns
  • (::String) — This system instruction is supported only for controllable/promptable voice models. If this system instruction is used, we pass the unedited text to Gemini-TTS. Otherwise, a default system instruction is used. AI Studio calls this system instruction, Style Instructions.

#ssml

def ssml() -> ::String
Returns
  • (::String) — The SSML document to be synthesized. The SSML document must be valid and well-formed. Otherwise the RPC will fail and return [google.rpc.Code.INVALID_ARGUMENT][google.rpc.Code.INVALID_ARGUMENT]. For more information, see SSML.

    Note: The following fields are mutually exclusive: ssml, text, markup, multi_speaker_markup. If a field in that set is populated, all other fields in the set will automatically be cleared.

#ssml=

def ssml=(value) -> ::String
Parameter
  • value (::String) — The SSML document to be synthesized. The SSML document must be valid and well-formed. Otherwise the RPC will fail and return [google.rpc.Code.INVALID_ARGUMENT][google.rpc.Code.INVALID_ARGUMENT]. For more information, see SSML.

    Note: The following fields are mutually exclusive: ssml, text, markup, multi_speaker_markup. If a field in that set is populated, all other fields in the set will automatically be cleared.

Returns
  • (::String) — The SSML document to be synthesized. The SSML document must be valid and well-formed. Otherwise the RPC will fail and return [google.rpc.Code.INVALID_ARGUMENT][google.rpc.Code.INVALID_ARGUMENT]. For more information, see SSML.

    Note: The following fields are mutually exclusive: ssml, text, markup, multi_speaker_markup. If a field in that set is populated, all other fields in the set will automatically be cleared.

#text

def text() -> ::String
Returns
  • (::String) — The raw text to be synthesized.

    Note: The following fields are mutually exclusive: text, markup, ssml, multi_speaker_markup. If a field in that set is populated, all other fields in the set will automatically be cleared.

#text=

def text=(value) -> ::String
Parameter
  • value (::String) — The raw text to be synthesized.

    Note: The following fields are mutually exclusive: text, markup, ssml, multi_speaker_markup. If a field in that set is populated, all other fields in the set will automatically be cleared.

Returns
  • (::String) — The raw text to be synthesized.

    Note: The following fields are mutually exclusive: text, markup, ssml, multi_speaker_markup. If a field in that set is populated, all other fields in the set will automatically be cleared.