Discussions

I have a simple script which I'm running on Spck Editor app. Its a bus times table. This script works well, although I'd like to improve it by adding a text to speech function. So it reads out the next bus times once they have been printed. I have an API and User ID but I keep getting the error - PlayHT not defined? What can I do about this?

Hi, today there is any way to user a streamed (<https://docs.play.ht/reference/nodejs-streaming>) non english voices Ex: standard model with voice id 'pt-BR-DonatoNeural'? How can I get an official road map for releases of pt-BR voices in streamed models like PlayHT2.0-turbo. Regards, Joselito Ribeiro

I am brand new to this as a free user to try this out. How do I get a voice for my script? I have no idea where to begin. Your site was refered to me by a seasoned YouTuber.

Sometimes in My PLayHT api call I am getting this error , what could be causing this error : :confused: error: 8 RESOURCE_EXHAUSTED: Exhausted worker capacity {"code":8,"details":"Exhausted worker capacity","metadata":{"content-length":["0"],"content-type":["application/grpc"],"date":["Mon, 08 Jul 2024 16:47:47 GMT"],"server":["awselb/2.0"]},"timestamp":"2024-07-08T16:47:48.016Z"}

Can you provide an endpoint to retrieve subscription information, including the number of characters used and the character limit? I want to display this information directly in my application.

I wouldl like to be able to edit advanced voice controls to all segments of the file in a similar way that we either change the speed of a specific segement or we can change the speed of all segments in the file. Does anyone know if this is possible? If so, how to execute this? Thanks :)

Trying to generate with this endpoint (not the V2 one): <https://docs.play.ht/reference/api-convert-tts-standard-premium-voices> <br /> {"error":"You don't have access to this API"} <br /> How do I fix this? <br /> import requests url = "<https://api.play.ht/api/v1/convert"> payload = { "content": ["Hey you!"], "voice": "ja-JP-Wavenet-C" } headers = { "accept": "application/json", "content-type": "application/json", ..... } response = requests.post(url, json=payload, headers=headers) print(response.text)

Trying to generate with this endpoint (not the V2 one): <https://docs.play.ht/reference/api-convert-tts-standard-premium-voices> <br /> {"error":"You don't have access to this API"} <br /> How do I fix this? <br /> import requests url = "<https://api.play.ht/api/v1/convert"> payload = { "content": ["Hey you!"], "voice": "ja-JP-Wavenet-C" } headers = { "accept": "application/json", "content-type": "application/json", ..... } response = requests.post(url, json=payload, headers=headers) print(response.text)

Trying to generate with this endpoint (not the V2 one): <https://docs.play.ht/reference/api-convert-tts-standard-premium-voices> <br /> {"error":"You don't have access to this API"} <br /> How do I fix this? <br /> import requests url = "<https://api.play.ht/api/v1/convert"> payload = { "content": ["Hey you!"], "voice": "ja-JP-Wavenet-C" } headers = { "accept": "application/json", "content-type": "application/json", ..... } response = requests.post(url, json=payload, headers=headers) print(response.text)

Hi Team Is there a limit on the number of concurrent connections that can be opened using WebSocket or using the tts.Stream API (bidirectional GRPC)? When using stream API or WebSockets what is the preferred way of making requests, is it sending individual tokens as and when streamed from LLM service or aggregating tokens to get sentences and then making the request?