Native Voice Artists for multiple languages
Budget: $35 – $55 USD
We are seeking talented native voiceover artists to contribute to the development of a text-to-speech model. This remote, project-based role involves recording one hour of clear, high-quality speech in the following languages while strictly adhering to our technical guidelines.
We need voice artists for the following languages:
- Gujarati
- Kannada
- Malayalam
- Punjabi
- Telugu
- Marathi
Note: If you are a native speaker of any of the languages mentioned, you are welcome to apply for that specific language.
* Apply with a 30-second audio sample in any of the above languages that meets all the following requirements:
Essential Requirements:
* Format: 44.1 kHz, 24-bit depth, Mono Output (Avoid Stereo Output), .WAV file format
* Recording Equipment Frequency Range: Full Spectrum from 20Hz to 20 kHz (Recordings below this will be rejected)
* Amplitude: -0.25 to 0.25 (Recordings below this will be rejected)
*Sound Quality: No Echo, background noise, music, EQ, and compression
* Clipping: Audio should not be clipped
* Pronunciation: Clear and precise and should have a native accent
Preferred Practices:
* Do not stand very close to the mic to avoid a thumping sound
* Remove retakes, clicks, and lip-smacking
* Keep natural breathing sounds, and maintain a steady, natural speech pace
* Avoid unnecessary pauses
* Record in a peaceful environment to avoid static noise
Usage Rights:
Recordings are for TTS training only, not for commercial use, and no cloning
We look forward to hearing from you.
We need voice artists for the following languages:
- Gujarati
- Kannada
- Malayalam
- Punjabi
- Telugu
- Marathi
Note: If you are a native speaker of any of the languages mentioned, you are welcome to apply for that specific language.
* Apply with a 30-second audio sample in any of the above languages that meets all the following requirements:
Essential Requirements:
* Format: 44.1 kHz, 24-bit depth, Mono Output (Avoid Stereo Output), .WAV file format
* Recording Equipment Frequency Range: Full Spectrum from 20Hz to 20 kHz (Recordings below this will be rejected)
* Amplitude: -0.25 to 0.25 (Recordings below this will be rejected)
*Sound Quality: No Echo, background noise, music, EQ, and compression
* Clipping: Audio should not be clipped
* Pronunciation: Clear and precise and should have a native accent
Preferred Practices:
* Do not stand very close to the mic to avoid a thumping sound
* Remove retakes, clicks, and lip-smacking
* Keep natural breathing sounds, and maintain a steady, natural speech pace
* Avoid unnecessary pauses
* Record in a peaceful environment to avoid static noise
Usage Rights:
Recordings are for TTS training only, not for commercial use, and no cloning
We look forward to hearing from you.