Feature Requests

This would be useful for telephony.

This is a feature request for a "voice changer" feature, sometimes called "speech-to-speech" in the industry. for Octave where, instead of uploading text, you could upload an audio file containing speech, and the output would reflect the input speech in some aspects (such as the text, timing and inflection) but reflect the Octave voice in other aspects (tone, timbre, accent)

i can't get it to slow down the pace with the acting instructions or with .... so some type of markup would be nice to specify number of seconds

If the last letter or letters of a word end in s or s, and the word is plural, there is a tendency for the pronunciation of the word to sound like partiessss.

This feature request is to provide timing data similar to what ElevenLabs provides: * Timing information about the timestamps in the audio of when the speech reaches a certain point, at the character level. * Alignments i.e. -- "lipsync" data that helps in knowing what the shape of the mouth would be at each timestamp if somebody were to speak this audio. * Possible support for formats like SRT?

I want ChatGPT to assign emotions to the text. For example - Hello, friend {Sad voice}. Then I want to upload this text to the Text-to-Speech section on the Hume AI website so that I don't have to mark each paragraph manually, and by clicking the generate button, I can immediately get the corresponding emotions for the text.

Unable to export audio: Audio generation failed due to an internal error

Currently, I can't find an option to rename a voice I created.

The python API is not the most intuitive, maybe use standardized formats? E.g. from pathlib import Path from openai import OpenAI client = OpenAI() speech_file_path = Path(__file__).parent / "speech.mp3" response = client.audio .speech.create( model="tts-1", voice="alloy", input="Today is a wonderful day to build something people love!" ) response.stream _to_file(speech_file_path)