Which agents work with it?

Any agent that reads skills from a directory. Claude Code, Codex and Gemini CLI read it natively; Cursor and VS Code connect over MCP.

The voice runs on your own machine, so there is nothing to meter. The first run downloads it, about 340 MB.

Yes. The skill is MIT-licensed and the authoring format is public.

Hear every voice before you pick one

36 voices your presentations can speak in. Tap any one to hear it, or play them back to back and stop when one sounds right.

Booth1 of 12

Heart

American female

0:000:03

Booth

Small & quick

12 voices · Free · unlimited · on your computer. Each voice reads the same sentence, so you hear the voice and not the script.

Runs on Kokoro 82M.

Studio

Rich & natural

9 voices · Free · unlimited · on your computer. Each voice reads the same sentence, so you hear the voice and not the script.

Runs on Qwen3-TTS, 0.6B or 1.7B.

Premium cloud

Best in class

15 voices · Paid · uses narration credits.

Runs on ElevenLabs Multilingual v2.

The models behind each tier

Booth and Studio run on your own computer through bisque-voice, our open-source speech engine, so they cost nothing and your script never leaves your machine. Premium cloud is synthesized by ElevenLabs.

Booth

Kokoro 82M

Runs on: Your computer, CPU is enough
Download: About 340 MB
Languages: 9; the voices here speak English
Word timings: Reported by the model as it speaks
Engine id: kokoro

Studio

Qwen3-TTS CustomVoice, 0.6B or 1.7B

Runs on: Your computer
Download: 1.3 GB or 2.3 GB
Languages: 10, including Chinese, Japanese and Korean
Word timings: Measured from the finished audio by a forced aligner
Engine id: qwen3-voices-06b, qwen3-voices-17b

Premium cloud

ElevenLabs Multilingual v2

Runs on: ElevenLabs' servers
Download: None
Languages: 29
Word timings: Returned by ElevenLabs with the audio
Engine id: elevenlabs, model eleven_multilingual_v2

Studio can also speak in your own voice, cloned from a 10 to 30 second recording.

curl -fsSL https://download.bisque.today/bisque-voice/install.sh | sh
bisque-voice install kokoro
bisque-voice --text "Hello there." --voice kokoro:af_heart --out hello.mp3