Unlocking your potential with the power of AI voice.

• Higher Quality Voice Clones will provide access to higher precision cloning that can deliver any voice a user can think of.
• Multi-user features give creative unit leaders the flexibility to distribute parts of a project among multiple team members under the same Pro business account.
• Multi-lingual Synthesis provides the capacity to render audio in multiple languages, ideal for localization use cases
• Pro-Level Support offers dedicated customer support that ensures you're not held up by any problems, big or small. Our team are ready to help.
• Team Collaboration enables cooperation among team members, sharing of workload, build supervision and approval of scenarios.

Prepare your environment

• Keep down background noise to a minimum whilst recording. You should choose a silent room to record your training material.
• You can cover the head and microphone with a cloth to filter ambient noise.
• Covering the sides of your room will avoid sound waves reflecting and creating audio artifacts. Thick curtains or drapes may do the trick. You can also speak into your curtains if you don't want to move the room around.
• If possible, ceiling isolation is also handy. It makes sure the sound does not echo from above. Our users have tried placing panels or cardboard egg boxes in their recording space.

Gear up for a good quality audio

• Not got recording gear? All is not lost. You can record audio using your mobile device. Generally, phones have better microphones than webcams for laptops.
• If you want to invest in recording gear, it is possible to buy an optimal microphone for less than 100 USD.
• Keep a distance from your microphone. One foot (30 cms) is ideal for a better audio recording.
• Cover your mics with a puff or pop filter (available cheap online). This will significantly reduce most of the plosives on your recording.

Speak clearly

• Avoid long pauses.
• Stuttering or stammered? Try again! You only need a couple of seconds to train your clone. Take as much time as you need to keep the speech clear and smooth.

Clones may sound differently

• Cloned voices will have an American English accent. Voice cloning copies only the timbre of your voice, not the speaking style, language, or dialect.
• Many of us are not familiar with how their own voice sounds to other people. You can download your input voice using the Voice Cloning sidebar.

Check out for more tips

• We encourage you to subscribe to our YouTube Channel
• Why not join our Discord channels? You can reach out to us and many other fellow users of Coqui.

• The AI Voice Dropdown is on the left hand side of each line and allows choosing from built-in or custom AI voices to synthesize the text.
• Voice Cloning allows the user to create an artificial simulation of another person's voice from just 3 seconds of an input audio file.
• With Prompt-to-Voice new custom AI Voices can be created simply by describing them with text.
• Voice Fusion merges two distinct AI voices together to create something totally unique.
• Emotion Presets contain predetermined emotions (Neutral, Happy, Angry, Sad, Surprise, and Dull) which can be assigned to each line.
• Energy is the volume of the voice and it can be edited using the Advanced Editor
• Phoneme Editor is the editing mode with the highest granularity in the Advanced Editor. It’s based on “phonemes” of the pronounced text, which correspond to any consonant or vowel sound in a word.
• Pitch is the tone of the voice that indicates whether the voice is high or low. Fine tuning is available using the Advanced Editor.
• Scripts can be divided into Scenes.
• The synthesized audio for a given scene, including pauses between lines, can be exported into a single audio file.
• Each line has a corresponding Speech Rate, which can be changed to control how slowly or quickly the line text will be read by the AI Voice.
• Take management lets users save and manage multiple performances for a single line.
• With the Timeline Editor you can arrange your scene into a dialogue, editing dramatic pauses between lines and playing the entire scene at once.

• All Supported Languages service provides a tailormade selection of languages that the customer audio production pipeline requires.
• API access is available for software development teams to integrate Coqui Studio capabilities to their software systems programmatically.
• Audit Logs are used to log records of events or actions that occur within Coqui Studio.
• Custom Integrations are available for a user’s needs, to optimise workflow continuity over various softwares and platforms.
• Premium Quality Voice Clones are high-fidelity synthetic voices that mimic the speech and intonation of real people chosen by the user.
• Role-Based Access (RBAC) capability helps the enterprise organization to assign permissions to access to the company's creative resources and pipelines by choosing different user levels.
• Script Versioning is a process of tracking and managing changes in scripts over time.
• Single Sign On (SSO) uses the enterprise authentication scheme to allow multiple users to log in to Coqui Studio with their own single IDs.
• Team Management Tools lets teams that collaborate on different creative pipelines (narrative direction, localization, audio engineering, animation, post-production etc.) connect.
• Virtual Private Cloud Hosting is a service that hosts Coqui Studio assets and resources on a virtual private cloud network that is isolated from other users of the platform.