Supported formats
Upload standard audio and video types: MP4, MOV, MP3, WAV. If your source uses a rare container or codec, transcode to MP4 with H.264 video and AAC audio to avoid import issues.
Size and length limits
There is no maximum upload size per file. However, you should make sure you have enough tokens to translate the video🤝.
Audio quality, for accurate transcription and voice cloning
Record clear, intelligible speech at a natural pace.
Do not let speakers overlap; alternate turns to keep the transcript clean.
Include at least 30 seconds of speech per speaker for robust voice cloning.
Video quality, if you plan to use Lip-Sync later
Lip-sync works best when the active speaker faces the camera. A frontal view yields the most accurate mouth alignment. Ensure overall image quality is good.
Background sounds and noise handling
CHAMELAION automatically separates clean speech from other sounds and removes background noise. You can decide later whether to mix music and ambience back in during export.
Account and workspace basics that impact uploading
Your free tokens and plan limits apply to processing. You can check remaining tokens and the next refill cycle under your profile.
If you need more tokens, you can purchase them on the Plans page.
Your plan governs monthly translation or dubbing capacity. For details and top-ups, see Plans or the Pricing, Billing and Invoicing collection.
If you are unsure about what Plan fits best for you, use our Calculator on the Plans page 👍.
Recommended prep checklist
File is MP4, MOV, MP3, or WAV, or has been transcoded to MP4, H.264, AAC.
Clear speech, no overlapping talk, ≥ 30 s per speaker for cloning.
If Lip-Sync is desired later, ensure the footage is mostly frontal for optimal results.
Make sure that you have enough Tokens for what you want to do. If you need more, you can buy extra Tokens through the Plans page at any time😉.
That is it for requirements. Where to go from there? Visit our other Help Centre Articles for more information on CHAMELAION's features💯.