#text to speech api

1 messages · Page 1 of 1 (latest)

vestal ginkgo
#

is text-to-Speech Websocket API only works for backend?

fluid finchBOT
#

Hi @vestal ginkgo. I'm kapa.ai, your friendly support bot. I will try to answer your question by searching through the knowledge base. :wave:

scenic sealBOT
#

Hey there! This channel allows you to ask Kapa.ai for assistance. But it looks like you haven't connected your Discord profile to your Deepgram account yet. You can do so at https://community.deepgram.com - by doing so, you'll be able to ask questions in #1115960287183511643 if you need human assistance!

Deepgram Community

Deepgram’s community offers tons of resources to support you on your voice AI journey

fluid finchBOT
#

No, Deepgram's Text-to-Speech WebSocket API is not limited to backend use only. It can be used in various environments including frontend and backend applications. The API is designed to provide a real-time, interactive solution for converting streaming text to speech, which is ideal for applications that require immediate audio feedback and continuous data streams, such as live customer service chatbots and interactive voice response (IVR) systems source (https://developers.deepgram.com/docs/tts-websocket).

Deepgram provides SDKs for different languages including JavaScript (which can be used in frontend development), Python, .NET, and Go. These SDKs include support for the Text-to-Speech Streaming API source (https://developers.deepgram.com/docs/sdk-feature-matrix#text-to-speech-streaming-api).

For example, in a JavaScript frontend application, you could establish a WebSocket connection to the Deepgram API, send text data to be converted to speech, and then receive the audio data in real-time. This could be used to provide immediate audio feedback to the user based on their interactions with the application.

Remember to follow the guidelines provided in the Deepgram documentation when using the API, such as using one WebSocket per conversation for conversational AI use cases source (https://developers.deepgram.com/reference/transform-text-to-speech-websocket#use-one-websocket-per-conversation).

Note: you can ask me a follow up question by @ mentioning me again :speech_balloon:

#

@vestal ginkgo Kapa.ai is still learning and improving, please let me know how I did by reacting below.