Jammable

O que é Jammable?

Jammable is a web platform for converting audio into AI vocal covers and generating speech from text. Choose a voice model, supply audio you have permission to use, and generate a cover; custom training and multi-voice duets support different vocal arrangements. Its community library can be searched by category, while paid tiers add training, videos, or priority processing. The published terms restrict use to domestic and private purposes and require rights to uploaded content. A model in the library is not an endorsement or third-party licence.

O que Jammable pode fazer?

AI vocal covers

Convert supplied audio with a selected model. Cover outputs include the full mix, converted vocals, and the instrumental for further listening or mixing.

Community voice selection

Browse voice models and collections by name or categories such as music, cartoon, gaming, anime, and language.

Duets and text-to-speech

Combine multiple selected voices in a cover or create spoken audio from text. API speech requests support up to 2,500 characters.

Custom voice training

Creator and Power support unlimited training from vocal samples. Uploaded voice libraries can be shared with other users or kept private; private does not mean local-only processing.

Shareable videos and processing

Creator includes 50 video coins per month. Power adds unlimited video coins, priority processing at 250 covers per 12 hours, and $25 of monthly API balance.

Generation API

Submit cover or speech jobs, search voices, check status, and retrieve audio through the REST API. Cover jobs return separate mix, vocal, and instrumental files.

Casos de uso

“Compare vocal arrangements”

Generate alternate vocal versions of audio you own or have permission to use, then review the results.

“Build a multi-voice cover”

Combine selected voice models in one duet-style vocal arrangement.

“Create a custom-voice personal project”

Train an authorized vocal sample and use the model for covers or spoken clips within the permitted use scope.

“Programmatic personal audio projects”

Submit a supported audio URL or text through the API and retrieve the generated files. API access does not remove the non-commercial use or content-rights conditions.

Perguntas frequentes

What do the USD subscriptions cost?

Basic is $1.99 for the first month, then $8.99 per month. Creator is $9.99 for the first month, then $24.99 per month. Power is $89.99 per month. Plans renew monthly; cancel at any time and benefits continue until the billing period ends.

What can I do without a plan?

Browse and hear voice models. Making covers, downloading them, text-to-speech, and duets require a plan. Free registration and voice previews do not include free audio generation.

How is the API billed?

Covers and speech cost $0.25 per audio minute, billed by the second with a $0.10 minimum per completed job. Failed jobs are free. Top-ups start at $10, and Power includes $25 of API balance each month.

What audio does the API accept?

Provide a publicly accessible audio-file URL, such as MP3 or WAV. YouTube and streaming links are not supported. Download completed output within seven days.

Does paying for a plan grant commercial or third-party rights?

No. The published terms restrict services to domestic and private use, not commercial or business purposes. You need the rights, permissions, and consents for uploaded audio and voice material. A community model or paid subscription does not grant rights from the person, character, or music owner it resembles.