Discussions

Ask a Question

Cloning a Voice Results in Error

I have tried the Instant Cloning feature. I upload a one minute high quality voice clip and when I press "Finish Clone" a red error box pops up and I can never finish. ANy help is appreciated.

Emotions with api?

Hello, when we use the app in the studio there is a option to add emotions like - Happy,Sad,Angry,Disgust,Fear,Surprise Is it possible to add them with the api? like in a parameter? there isn't anything about them in the docs

How to have correct english pronouncements inside a german text?

I've tried to figure out with the support-chat but this also seems to be an A.I. - it can't help. So i hope to reach a human being here who could solve the question. So, when i have – and thats absolutely usual nowadays – english words in a german text, these words are spoken out in a heavy, robotic and just unusable german slang.

Custom pronunciations with API

Hi, I'm trying to figure out how I can specify custom pronunciations with the PlayHT2.0 engine via the API. I can't find it in the docs.

Will this support song singing based on lyrics

I want to use this API to make me sing a song

Unable to run sample demo using format="mp3"

If i leave it off, it defaults to WAV (or maybe MP3 inside WAV as the docs claim MP3 is default, but it is clearly a WAV file). But i would like just mp3. Per the example. I'm getting this python run-time exception: File "/Library/Frameworks/Python.framework/Versions/3.12/lib/python3.12/site-packages/pyht/client.py", line 108, in stream_tts_input yield from self.tts(buffer.getvalue(), options, voice_engine) File "/Library/Frameworks/Python.framework/Versions/3.12/lib/python3.12/site-packages/pyht/client.py", line 137, in tts params = api_pb2.TtsParams( ^^^^^^^^^^^^^^^^^^ ValueError: unknown enum label "mp3"

Subscription problem.

can I export custom cloned voice line while a $5.00 API subscription plan on the PlayHT app?

V2.1 Model is generating weird output

Hey I am getting this behavior my local machine and on Play.HT API doc, anyone faced this issue before ? Output: ``` ID3#TSSELavf58.29.100����d�9�Z���t��9'V�ӖoY��f�Y�pm�����4f �`њ(hΙ�&\��&də2fL��&dƝ�r����jQ��k9��R��c �%�0��A �1� Y�����>�j��:��:E�������b�T���w���T鎠�8���������@"�S�uN�� 1�A111b,u�T�S�u��ؚ�]��9C���gl��r��;]�Q1"�b �;���嵶��z�k���b�,Eػ�gl흹n[�������9C��?���n[��n[��9C8r�!�k�Mw��&���;gm}�3�ػcg �16v��z�]�w�5��b�]��v3����z�]뽉��v��p��8g q�w�-���v�ܷ-�r����\r��$:����`�&b�`[�8`�  ��#�.�Ɇ�X=1�� ��� �`�f n80����?q1�+��P<0*���P �զE�x  ��`p�L@�&ؼe���� ��dXT%��0�J��%W�5" �K2"��� )�/������k��N�W�d�i��"�R�Kq�<LM�@CfN� 4xȦ3#�Ɖ"� l�c������h��fjH6��[�(��Z���� 72i �`s(�CF � ˘#O�D�m}�Uv�Tq�2f`BU$�l � �Aً(� �2Ĝ0(��T�����Bi͒5�_�>�#���\�����Z�? j����^t�mY�;jd����@|!��T�;����<�� ��C�j�|��軬$�.ge�\��sb��}Z�]���f��o��iG3���?u뤤�U7F�Ī�0��,<��UCQ�S"@s@���ӌ�"`�� ����L(�`P`�U 9��(x h���Vj�i���*��`(-����Mx�65c��aP�� fC(� \c��@ �W�4&`�2� c���F�Ttf�a���W�:�d�1�����2w�g�&'�Q��� ���@�˼a`�aQY�@�u��4 PH�h.a��@f'8H4 �L8" �50�\1�4�B2嫴(AƘ��� �  0�A1��� ��âʁ���Ql����\b�J�������n~)f~(���f~��p �N �``����!�8v[�Ap0�8.Ì}�x�_w�r��?n�ˋ�1R��]���4�� ���ۄAI���x4D7  D�0l Z����(��<n~Q��s a�����A��uΦ��7�kqw~G��a�@�PV��R��-ک�i�a�|��hT�J,��TɂC�#���m$C��#6�C@��C“ �Q�?C��c�X@0R3�1h����<t D��1�c0�1 .�0�� ���̄d� �Q�͜ � �XM�t�g�ƈ�g�&�^b�L&e�fF�|(fI4}�8`jd���r4&",! ����D�0,�DE@@SLP��}!� ��ā���<!6 ����tZD� F����"b"4 �A Dȅ��O`���‚��C �DbA�D�s( "/���@�c�@c! �3f�.��tW,1,l̝�`��a�I���S��b��R��>M^*�0Z�W�x���>'�h 1Q 5��JE�e�6@0#|��`�Y𞩠�Őb i�#9.��EQu_,�d0�����6�e�������X)��lB��%���Y"E�u�hp�$�Z\)�=�2 �ݔ��9��m�RX��� ���8����q�bq�.q�����0�� ��1�*��sj`H�O��L ǂ�����>q :T��. �#�zU� D� ¢� F ```

Playht is generating text to speech but not speaking in the web browser I am using

Hi everyone, I am building an AI assistant in the browser and I the speech generated goes to the transcribed files in the playht website but don't display in my browser. The speeches are being generated correctly, the problem is that they are not being played in the browser where I am using the app.

failed to export chunk using python SDK

from pyht import Client from dotenv import load_dotenv from pyht.client import TTSOptions import os load_dotenv() client = Client( user_id=os.getenv("PLAY_HT_USER_ID"), api_key=os.getenv("PLAY_HT_API_KEY"), # for on-prem users, uncomment and add the advanced grpc_addr option below. Replace grpc_addr with your endpoint. # advanced=client.Client.AdvancedOptions(grpc_addr="{your-endpoint}.on-prem.play.ht:11045") ) options = TTSOptions(voice="s3://voice-cloning-zero-shot/d9ff78ba-d016-47f6-b0ef-dd630f59414e/female-cs/manifest.json") for chunk in client.tts("Can you tell me your account email or, ah your phone number?", options): # do something with the audio chunk print(type(chunk)) Have tried the above code but unable to create or export the wav/mp3 file. Suggest is there way to export or play the file