Class: Telnyx::Resources::TextToSpeech

Inherits:

Object

• Object
• Telnyx::Resources::TextToSpeech

Defined in:

lib/telnyx/resources/text_to_speech.rb

Overview

Text to speech streaming command operations

Instance Method Summary

• #generate(aws: nil, azure: nil, disable_cache: nil, elevenlabs: nil, language: nil, minimax: nil, output_type: nil, provider: nil, resemble: nil, rime: nil, telnyx: nil, text: nil, text_type: nil, voice: nil, voice_settings: nil, request_options: {}) ⇒ Telnyx::Models::TextToSpeechGenerateResponse

  Some parameter documentations has been truncated, see Models::TextToSpeechGenerateParams for more details.

• #initialize(client:) ⇒ TextToSpeech constructor private

  A new instance of TextToSpeech.

• #list_voices(api_key: nil, provider: nil, request_options: {}) ⇒ Telnyx::Models::TextToSpeechListVoicesResponse

  Retrieve a list of available voices from one or all TTS providers.

Constructor Details

#initialize(client:) ⇒ TextToSpeech

This method is part of a private API. You should avoid using this method if possible, as it may be removed or be changed in the future.

Returns a new instance of TextToSpeech.

Parameters:

• client (Telnyx::Client)

# File 'lib/telnyx/resources/text_to_speech.rb', line 109

def initialize(client:)
  @client = client
end

Instance Method Details

#generate(aws: nil, azure: nil, disable_cache: nil, elevenlabs: nil, language: nil, minimax: nil, output_type: nil, provider: nil, resemble: nil, rime: nil, telnyx: nil, text: nil, text_type: nil, voice: nil, voice_settings: nil, request_options: {}) ⇒ Telnyx::Models::TextToSpeechGenerateResponse

Some parameter documentations has been truncated, see Models::TextToSpeechGenerateParams for more details.

Generate synthesized speech audio from text input. Returns audio in the requested format (binary audio stream, base64-encoded JSON, or an audio URL for later retrieval).

Authentication is provided via the standard ‘Authorization: Bearer <API_KEY>` header.

The ‘voice` parameter provides a convenient shorthand to specify provider, model, and voice in a single string (e.g. `telnyx.NaturalHD.Alloy` or `Telnyx.Ultra.<voice_id>`). Alternatively, specify `provider` explicitly along with provider-specific parameters.

Supported providers: ‘aws`, `telnyx`, `azure`, `elevenlabs`, `minimax`, `rime`, `resemble`.

The Telnyx ‘Ultra` model supports 44 languages with emotion control, speed adjustment, and volume control. Use the `telnyx` provider-specific parameters to configure these features.

Parameters:

• aws (::Telnyx::Models::TextToSpeechGenerateParams::Aws) —

  AWS Polly provider-specific parameters.

• azure (::Telnyx::Models::TextToSpeechGenerateParams::Azure) —

  Azure Cognitive Services provider-specific parameters.

• disable_cache (Boolean) —

  When ‘true`, bypass the audio cache and generate fresh audio.

• elevenlabs (::Telnyx::Models::TextToSpeechGenerateParams::Elevenlabs) —

  ElevenLabs provider-specific parameters.

• language (String) —

  Language code (e.g. ‘en-US`). Usage varies by provider.

• minimax (::Telnyx::Models::TextToSpeechGenerateParams::Minimax) —

  Minimax provider-specific parameters.

• output_type (Symbol, ::Telnyx::Models::TextToSpeechGenerateParams::OutputType) —

  Determines the response format. ‘binary_output` returns raw audio bytes, `base64

• provider (Symbol, ::Telnyx::Models::TextToSpeechGenerateParams::Provider) —

  TTS provider. Required unless ‘voice` is provided.

• resemble (::Telnyx::Models::TextToSpeechGenerateParams::Resemble) —

  Resemble AI provider-specific parameters.

• rime (::Telnyx::Models::TextToSpeechGenerateParams::Rime) —

  Rime provider-specific parameters.

• telnyx (::Telnyx::Models::TextToSpeechGenerateParams::Telnyx) —

  Telnyx provider-specific parameters. Use ‘voice_speed` and `temperature` for `Na

• text (String) —

  The text to convert to speech.

• text_type (Symbol, ::Telnyx::Models::TextToSpeechGenerateParams::TextType) —

  Text type. Use ‘ssml` for SSML-formatted input (supported by AWS and Azure).

• voice (String) —

  Voice identifier in the format ‘provider.model_id.voice_id` or `provider.voice_i

• voice_settings (Hash{Symbol=>Object}) —

  Provider-specific voice settings. Contents vary by provider — see provider-speci

• request_options (Telnyx::RequestOptions, Hash{Symbol=>Object}, nil)

Returns:

• (Telnyx::Models::TextToSpeechGenerateResponse)

See Also:

• Models::TextToSpeechGenerateParams

# File 'lib/telnyx/resources/text_to_speech.rb', line 66

def generate(params = {})
  parsed, options = Telnyx::TextToSpeechGenerateParams.dump_request(params)
  @client.request(
    method: :post,
    path: "text-to-speech/speech",
    body: parsed,
    model: Telnyx::Models::TextToSpeechGenerateResponse,
    options: options
  )
end

#list_voices(api_key: nil, provider: nil, request_options: {}) ⇒ Telnyx::Models::TextToSpeechListVoicesResponse

Retrieve a list of available voices from one or all TTS providers. When ‘provider` is specified, returns voices for that provider only. Otherwise, returns voices from all providers.

Some providers (ElevenLabs, Resemble) require an API key to list voices.

Parameters:

• api_key (String) —

  API key for providers that require one to list voices (e.g. ElevenLabs).

• provider (Symbol, Telnyx::Models::TextToSpeechListVoicesParams::Provider) —

  Filter voices by provider. If omitted, voices from all providers are returned.

• request_options (Telnyx::RequestOptions, Hash{Symbol=>Object}, nil)

Returns:

• (Telnyx::Models::TextToSpeechListVoicesResponse)

See Also:

• Models::TextToSpeechListVoicesParams

# File 'lib/telnyx/resources/text_to_speech.rb', line 94

def list_voices(params = {})
  parsed, options = Telnyx::TextToSpeechListVoicesParams.dump_request(params)
  query = Telnyx::Internal::Util.encode_query_params(parsed)
  @client.request(
    method: :get,
    path: "text-to-speech/voices",
    query: query,
    model: Telnyx::Models::TextToSpeechListVoicesResponse,
    options: options
  )
end