with Azure OpenAI and IBM Cloud - Speech to Text?
Create completions for chat messages with the GPT-35-Turbo and GPT-4 models. See the documentation
Classify items into specific categories. See the documentation
Creates an image given a prompt, and returns a URL to the image. See the documentation
Summarizes a text message with the GPT-35-Turbo and GPT-4 models. See the documentation
Translate text from one language to another. See the documentation
The Azure OpenAI Service API provides access to powerful AI models that can understand and generate human-like text. With Pipedream, you can harness this capability to create a variety of serverless workflows, automating tasks like content creation, code generation, and language translation. By integrating the API with other apps on Pipedream, you can streamline processes, analyze sentiment, and even automate customer support.
import { axios } from "@pipedream/platform"
export default defineComponent({
props: {
azure_openai_service: {
type: "app",
app: "azure_openai_service",
}
},
async run({steps, $}) {
const data = {
"messages": [{ role: 'user', content: "Hello, world!" }],
}
return await axios($, {
method: "post",
url: `https://${this.azure_openai_service.$auth.resource_name}.openai.azure.com/openai/deployments/${this.azure_openai_service.$auth.deployment_name}/chat/completions?api-version=2023-05-15`,
headers: {
"Content-Type": `application/json`,
"api-key": `${this.azure_openai_service.$auth.api_key}`,
},
data,
})
},
})
The IBM Cloud - Speech to Text API transforms spoken language into written text, offering a powerful tool for creating transcriptions, enabling voice control and command features, and feeding speech into analytics platforms. With Pipedream, you can build automated workflows that leverage this capability, such as transcribing meetings in real-time, analyzing customer service calls for sentiment and keywords, or even creating subtitles for videos. The ability to connect with other apps on Pipedream allows for complex workflows that can turn spoken data into actionable insights or accessible content.
import { axios } from "@pipedream/platform"
export default defineComponent({
props: {
ibm_cloud_speech_to_text: {
type: "app",
app: "ibm_cloud_speech_to_text",
}
},
async run({steps, $}) {
const data = {
"text": `hello world`,
}
return await axios($, {
method: "post",
url: `${this.ibm_cloud_speech_to_text.$auth.instance_url}/v1/synthesize`,
headers: {
"Content-Type": `application/json`,
"Accept": `audio/wav`,
},
auth: {
username: `apikey`,
password: `${this.ibm_cloud_speech_to_text.$auth.api_key}`,
},
data,
})
},
})