Community Voices

Real human voices shared by the community. Use them with any voice cloning model for natural-sounding TTS.

Sign Up to Share Your Voice
0
Shared Voices
0
Contributors
0
Languages
0
Times Used

No community voices yet

Be the first to share your voice! Upload a recording and help build the community voice library.

Upload Your Voice

Sign up to share your voice with the community.

Bieži uzdoti jautājumi

Community voices are real human voices uploaded by TTS.ai users. Anyone can record and share their voice for others to use with our AI voice cloning models. It is a way to add unique, authentic voices to the TTS.ai library.

Sign in to TTS.ai, go to Community Voices, and click "Upload Your Voice." Record or upload 30-60 seconds of clean speech. After quality verification, your voice becomes available for others to use with voice cloning models.

Community voices work with all voice cloning models: Chatterbox, CosyVoice2, OpenVoice, Spark, GPT-SoVITS, IndexTTS-2, and Qwen3-TTS. Each model produces slightly different results, so users can try multiple options.

Yes. Your voice recording is stored securely and only used for voice cloning when someone generates speech with it. You can set your voice as private (only you can use it) or public (anyone can use it). You can delete your voice at any time.

Community voices marked as "public" can be used for personal and commercial projects. The voice owner grants usage rights when they make their voice public. Always check the specific voice listing for any restrictions noted by the owner.

Uploaded voices go through automated quality checks: minimum duration (30 seconds), noise level (SNR > 20dB), single speaker detection, and format validation. Voices that pass are marked as verified and made available for use.

Click the star rating on any voice card to rate it from 1 to 5 stars. Ratings help other users find the best voices. You must be logged in to rate. Your rating is saved and you can change it at any time by clicking a different star.

Yes. You can remove your uploaded voice at any time from your account settings. Once deleted, the voice will no longer be available for others to use. Any speech previously generated with your voice is not affected.

We accept WAV, MP3, FLAC, OGG, M4A, and WEBM files up to 50MB. For the best cloning quality, upload lossless WAV or FLAC files recorded at 44.1kHz or higher with minimal background noise.

Each account can upload up to 10 community voices. This limit ensures quality over quantity and keeps the review process manageable. If you need more, contact support.

Voice review typically takes 24-48 hours. Our automated system checks audio quality, duration, and single-speaker requirements. Once verified, your voice is immediately available in the community library.

Yes. Click "Clone" on any community voice to go directly to the voice cloning tool with the community voice pre-loaded as reference audio. Then enter any text and generate speech in that voice using any of our cloning models.
5.0/5 (1)

Gatavs sākt?

Pierakstīties bez maksas un saņemt 50 kredītus. Nav kredītkarte nepieciešama.