playHT and Eleven labs filler audio added #396
Conversation
* deprecate old hosted service - docs: remove hosted quickstarts + remove gen-Z phone number - remove hosted quickstarts / references in code * update readme
* adds hipaa compliance docs * update hipaa doc
| filler_audio_noise = FillerAudio( | ||
| BaseMessage(text="Noise"), | ||
| audio_data=convert_wav( | ||
| '/Users/mohammadaminroohi/miniconda3/envs/vocode_1/lib/python3.9/site-packages/vocode/streaming/pink BL.wav', |
There was a problem hiding this comment.
This is referencing a file that is not present in the source. Consider adding it to this PR.
| output_sample_rate=8000, | ||
| output_encoding=AudioEncoding.MULAW, | ||
| ), | ||
| synthesizer_config=ElevenLabsSynthesizerConfig(sampling_rate=8000, audio_encoding=AudioEncoding.MULAW), |
There was a problem hiding this comment.
This is referencing a file that is not present in the source. Consider adding it to this PR.
There was a problem hiding this comment.
Yeah done thanks for letting me know. Actually I was about to add background noise to the conversation here. The goal was to make the conversation more natural. But approach is not working since on the same time, either the noise is been sent to Twilio or the synthesized voice, not both simultaneously. Which make the conversation wired.
added base class and factory for noise canceling
add more models for noise canceling
Co-authored-by: Shobhit <[email protected]>
Better interruptions
|
This PR has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions. |
|
This PR has been automatically closed due to inactivity. Thank you for your contributions. |
No description provided.