Callirra Audio Studio brings speech, music and sound effects into the same creative world as your images and videos. It gives creators dedicated ways to explore what a project should sound like, from a short spoken introduction to a musical atmosphere or an expressive sound cue. Kokoro 82M, ElevenLabs Turbo 2.5, ElevenLabs Multilingual v2, Suno V6 and Suno Sounds offer five distinct starting points, connected by one account, one general credit balance and a private library for the results.
The moment a picture becomes a story
Sound changes the way a visual is experienced. A carefully chosen voice can make a product introduction feel personal. A musical phrase can lend momentum to a sequence of scenes. A small effect can draw attention to a movement, a reveal or a change in atmosphere. Audio Studio gives these decisions their own creative space, so the sound of a piece can develop with the same attention as its composition, color and motion.
That space matters for many kinds of work. An independent maker may want a welcoming line for a launch clip. A storyteller may be exploring the voice of a narrated sequence. A social creator may want a recognizable musical mood across a series. A designer may hear a particular sound in a visual concept long before the final edit exists. Voice, music and effects provide complementary routes into each of those ideas.
Voices with room for different kinds of expression
The speech selection brings Kokoro 82M together with ElevenLabs Turbo 2.5 and ElevenLabs Multilingual v2. Preset voices and their supported languages give spoken content a clear starting point. Kokoro’s named choices include American and British English alongside voices for Spanish, French, Hindi, Italian, Japanese, Portuguese and Chinese. The ElevenLabs options expose a verified preset voice selection, adding further possibilities for the tone and character of a spoken piece.
The creative value appears in the relationship between words and delivery. A concise description can become a welcoming introduction. A small observation can become narration that guides a viewer through a scene. Different supported voices invite creators to explore how formal, intimate, energetic or reflective a project should feel. The written line remains an essential creative ingredient, with the voice bringing its own presence to the final sound.
Music that develops the mood of a project
Suno V6 expands that palette into music. A composition can begin with a style, a title, a target duration and the supported choice of instrumental or vocal direction. Optional lyrics give vocal work another source of character. Those ingredients open a space for musical exploration around a brand, a scene or a personal idea, with the generated piece finding its own duration around the requested target.
Consider the different emotional possibilities around the same visuals: a gentle instrumental for an intimate portrait, a bright musical direction for a playful reveal, a slower atmosphere for a landscape study. Music gives the creator another way to define the audience’s experience. When a music task returns multiple tracks, each can be auditioned and used separately, allowing useful alternatives to remain part of the project’s creative material.
Small sounds with a strong creative role
Suno Sounds focuses on sound effects, adding another dimension to scene building. An effect can suggest a setting, emphasize an action or give an abstract animation a stronger sense of physical presence. Supported loop instructions provide an additional direction for suitable sound ideas. This focused sound layer is particularly useful when the central visual already works and the creator wants to deepen its atmosphere through a few carefully chosen details.
Finished audio belongs with the rest of your work
Audio Studio connects quoting, generation, auditioning, download and saving around the current task. Completed MP3 outputs enter the private asset library automatically and can be placed in a chosen collection. A narration, a favorite music direction and the visual material for a project can therefore stay together. Constellation carries that connection further through video and audio mixing, turning saved sound into part of a connected creative workflow.
Clear creative choices, a shared balance
Audio uses the same general credits as image and video creation. Listed speech rates are 0.093 credits per 1,000 input characters for Kokoro, 6 for ElevenLabs Turbo 2.5 and 12 for Multilingual v2; Suno V6 is listed at 9 credits per request and Suno Sounds at approximately 1.88. The quote shows the expected reservation, and settlement records the completed task’s charge. An amount above that reservation requires separate approval before the output unlocks, keeping the financial decision with the creator.
Welcome to a broader creative palette. Whether your first sound is a single spoken sentence or a new musical direction, we would love to hear how Audio Studio fits your work. Share your feedback and the improvements that would help your next project through our contact page.
Explore voice, music and effects in Audio Studio →
Connect sound and picture with Constellation →