Job Description
Description: We are hiring German voice actors to create recordings to help train internal Text-to-Speech (TTS) models. There will be NO public broadcast or paid usage, meaning no advertisements or online media. The recordings will be used for internal TTS research and development purposes. Non-broadcast, internal, in perpetuity. There will be NO public or paid usage, nor will your voice be used as any form of external facing TTS model. Project Scope : - Talents will be asked to read 2 types of scripts: Stories and Utterances. - Each utterance will have _1 and _2 variants, where it will be the same script with different voice direction. One talent must read both variants. - Stories will include performance cues for emotional expression and narrative tone. The talent must deliver a natural, expressive reading that follows the provided cues precisely. - Each story is approximately 5 minutes long. - Each utterance is approximately 5-15 seconds. - Talents must record 60% utterances and 40% stories to reach 3 hours. Audition & Selection Process:. - Submit an audition using the sampe script attached below. - Please submit auditions with the following audio specs: Format: WAV Sampling rate: 48 kHz Bit depth: 24 bit Codec: PCM (Uncompressed) Channels: 1 (mono) Noise floor level: estimate (max)-60 dB RMS No plugins, compression, or post-processing Clean recordings with minimal background noise, breaths, and clicks - The audio MUST be narrated by a human. AI is NOT allowed. - After you are selected, the three hours of audio will need to be delivered within one week.
Array