We provide sample scripts in the 'General', 'Chat' and 'Customer Service' domains for each language to help you prepare your recording scripts. For example, if you plan to record 2,000 sentences, 1,000 of them could be general sentences, another 1,000 of them could be sentences from your target domain or the use case of your application. We recommend the recording scripts include both general sentences and domain-specific sentences. It will give your custom neural voice a better chance of pronouncing those phrases well. However, if you use set phrases (for example, "You have successfully logged in") in your speech application, make sure to include them in your script. Your utterances don't need to come from the same source, the same kind of source, or have anything to do with each other. For a brief discussion of potential legal issues, see the "Legalities" section. The utterances in your script can come from anywhere: fiction, non-fiction, transcripts of speeches, news reports, and anything else available in printed form. Building a custom neural voice requires at least 300 recorded utterances as training data.
#Speech central lite full
The term "utterances" encompasses both full sentences and shorter phrases.
The starting point of any custom neural voice recording session is the script, which contains the utterances to be spoken by your voice talent. Your voice talent should be amenable to a work-for-hire contract for the project. Usually, you'll want to own the voice recordings you make. Listen to readings by existing voices to get an idea of what you're aiming for. However, this personality trait should be subtle and consistent. Using the Custom Neural Voice capability, you can train a model that speaks with emotion, so define the speaking styles of your persona and ask your voice talent to read the script in a way that resonates with the styles you want.įor example, a persona with a naturally upbeat personality would carry a note of optimism even when they speak neutrally. Work with your voice talent to develop a persona that defines the overall sound and emotional tone of the custom neural voice, making sure to pinpoint what "neutral" sounds like for that persona. Limit sessions to three or four days a week, with a day off in-between if possible. Recording voice samples can be more fatiguing than other kinds of voice work, so most voice talent can usually only record for two or three hours a day. They also need to be able to control their pitch variation, emotional affect, and speech mannerisms. Your voice talent must be able to speak with consistent rate, volume level, pitch, and tone with clear dictation. You can approach this ideal through good recording practices and engineering. Your recordings for the same voice style should all sound like they were made on the same day in the same room. The single most important factor for choosing voice talent is consistency. It's possible to create unique "character" voices, but it's much harder for most talent to perform them consistently, and the effort can cause voice strain. Choose voice talent whose natural voice you like. Choose your voice talentĪctors with experience in voiceover, voice character work, announcing or newsreading make good voice talent. The editor role isn't needed until after the recording session, and can be performed by the director or the recording engineer. If you want to make the recordings yourself, this article includes some information about the recording engineer role.
This guide assumes that you'll be filling the director role and hiring both a voice talent and a recording engineer. Prepares the script and coaches the voice talent's performance.įinalizes the audio files and prepares them for upload to Speech StudioĪn individual may fill more than one role. Oversees the technical aspects of the recording and operates the recording equipment. This person's voice will form the basis of the custom neural voice. There are four basic roles in a custom neural voice recording project: Role This guide is a roadmap for a process that will help you get good, consistent results.
#Speech central lite professional
Many small but important details go into creating a professional voice recording. Choose a voice talent who has experience making these kinds of recordings, and have them recorded by a recording engineer using professional equipment.īefore you can make these recordings, though, you need a script: the words that will be spoken by your voice talent to create the audio samples. It's vital that these audio recordings be of high quality. The central component of a custom neural voice is a large collection of audio samples of human speech.
#Speech central lite pro
See Custom Neural Voice project types for information about capabilities, requirements, and differences between Custom Neural Voice Pro and Custom Neural Voice Lite projects.Ĭreating a high-quality production custom neural voice from scratch isn't a casual undertaking.
0 kommentar(er)
