Mantenha tudo organizado com as coleções
Salve e categorize o conteúdo com base nas suas preferências.
Os agentes de voz do Dialogflow usam a
Speech-to-Text
para reconhecimento de fala,
que está incluída nos
preços do Dialogflow.
O Dialogflow seleciona automaticamente um modelo de reconhecimento de fala para você,
mas você pode especificar o modelo.
Se um modelo não for especificado explicitamente,
o Dialogflow vai selecionar automaticamente um modelo com base na
configuração de áudio nas solicitações de API e nas configurações do agente.
Se o
modelo de fala aprimorado
estiver ativado para o agente
e não existir uma versão aprimorada do modelo especificado para o idioma,
a fala será reconhecida usando a versão padrão do modelo especificado.
Os modelos a seguir normalmente têm a melhor performance:
telephony_short (melhor para o Dialogflow de telefonia)
telefonia (melhor para o Agent Assist)
phone_call (bom para o Agent Assist e o Dialogflow de telefonia)
latest_short (melhor para Dialogflow não telefônico)
command_and_search (melhor para idiomas em que outros modelos não estão disponíveis)
Especificar um modelo
É possível fornecer o modelo ao chamar os métodos
detectIntent ou streamingDetectIntent
no tipo
Sessions,
ou ao configurar o
ConversationProfile
para
Agent Assist.
[[["Fácil de entender","easyToUnderstand","thumb-up"],["Meu problema foi resolvido","solvedMyProblem","thumb-up"],["Outro","otherUp","thumb-up"]],[["Difícil de entender","hardToUnderstand","thumb-down"],["Informações incorretas ou exemplo de código","incorrectInformationOrSampleCode","thumb-down"],["Não contém as informações/amostras de que eu preciso","missingTheInformationSamplesINeed","thumb-down"],["Problema na tradução","translationIssue","thumb-down"],["Outro","otherDown","thumb-down"]],["Última atualização 2025-08-18 UTC."],[[["\u003cp\u003eDialogflow voice agents utilize Speech-to-Text for speech recognition, which is factored into Dialogflow's pricing.\u003c/p\u003e\n"],["\u003cp\u003eWhile Dialogflow automatically chooses a speech recognition model, users have the option to select a specific model.\u003c/p\u003e\n"],["\u003cp\u003eThe best-performing models typically include \u003ccode\u003etelephony_short\u003c/code\u003e, \u003ccode\u003etelephony\u003c/code\u003e, \u003ccode\u003ephone_call\u003c/code\u003e, \u003ccode\u003elatest_short\u003c/code\u003e, and \u003ccode\u003ecommand_and_search\u003c/code\u003e, depending on the use case.\u003c/p\u003e\n"],["\u003cp\u003eA speech model can be set during API calls or when configuring the ConversationProfile for Agent Assist, dictating which model is used for speech recognition.\u003c/p\u003e\n"]]],[],null,["# Speech models\n\nDialogflow voice agents use\n[Speech-to-Text](/speech-to-text/docs)\nfor speech recognition,\nwhich is included in\n[Dialogflow pricing](/dialogflow/pricing).\nDialogflow automatically selects a speech recognition model for you,\nbut you can optionally specify the model.\n\nAvailable models\n----------------\n\nAll available models are listed at\n[Speech-to-Text models](/speech-to-text/docs/transcription-model).\nSelect a model that is best suited to your domain and\n[supports your agent language and speech features](/speech-to-text/docs/speech-to-text-supported-languages).\n\nIf a model is not explicitly [specified](#specify),\nthen Dialogflow auto-selects a model based on\nthe audio configuration in API requests and agent settings.\nIf [enhanced speech model](/dialogflow/es/docs/speech-enhanced-models) is enabled for the agent and an enhanced version of the specified model for the language does not exist, then the speech is recognized using the standard version of the specified model.\n\nThe following models typically have the best performance:\n\n- telephony_short (best for telephony Dialogflow)\n- telephony (best for Agent Assist)\n- phone_call (good for Agent Assist and telephony Dialogflow)\n- latest_short (best for non-telephony Dialogflow)\n- command_and_search (best for languages where other models are not available)\n\nSpecify a model\n---------------\n\nYou can supply the model when calling the `detectIntent` or `streamingDetectIntent` methods on the [`Sessions`](/dialogflow/es/docs/reference/common-types#sessions) type; or when configuring the [`ConversationProfile`](/dialogflow/es/docs/reference/rpc/google.cloud.dialogflow.v2#google.cloud.dialogflow.v2.ConversationProfile) for [Agent Assist](/agent-assist/docs). **Note:** If you specify the model with a conversation profile, Agent Assist and the associated virtual agent use this model for all speech recognition."]]