Text to Speech
turns written text into spoken audio in a chosen voice
Generates spoken audio from text you type or paste, in a voice you choose: ElevenLabs’ default voices, its community Voice Library, synthetic voices made with Voice Design, or your own cloned voices. Voice Remixing changes an existing voice’s delivery, tone, gender or accent from a written prompt.
Where to turn off Text to Speech: see below.
ElevenCreative Studio
video and audio projects drafted by an AI agent from a written description
Creates video and audio projects, including generated video clips, images, narration, music and sound effects, which you then edit on a timeline. ElevenLabs: “Describe the project you want to create, and Studio Agent creates a first draft.”
Where to turn off ElevenCreative Studio: see below.
- Where to check the switch
- No switch found — look in your ElevenLabs settings or ask your administrator
Audio Native
a website player that reads your web pages aloud in an AI voice
A player added to your own website that reads the page aloud to visitors. ElevenLabs: “Audio Native is an embedded audio player that automatically voices content of a web page using ElevenLab’s Text to Speech service.”
Where to turn off Audio Native: see below.
Voice changer
re-voices a recording in a different voice
Takes an uploaded recording or live microphone input and re-voices it in another voice, keeping the original delivery. ElevenLabs: “Voice changer (previously Speech-to-Speech) allows you to convert one voice (source voice) into another (cloned voice) while preserving the tone and delivery of the original voice.”
Where to turn off Voice changer: see below.
Speech to Text
transcribes audio and video files
Transcribes uploaded audio or video files into text, detecting the language automatically, and can tag sounds such as laughter or applause. ElevenLabs: “With speech to text, you can transcribe spoken audio into text with state of the art accuracy.”
Where to turn off Speech to Text: see below.
Instant Voice Cloning
a copy of a person’s voice from a short recording
Copies a person’s voice from a short recording, after which any text can be spoken in that voice. Before saving, the user confirms they have the right and consent to clone the voice.
Where to turn off Instant Voice Cloning: see below.
Professional Voice Cloning
a trained, near-identical model of a person’s voice
Trains a dedicated model of the user’s own voice from about one to three hours of recordings, after which any text can be spoken in that voice; a verification step checks the voice belongs to the person creating the clone. ElevenLabs: “You can only create a Professional Voice Clone of your own voice.”
Where to turn off Professional Voice Cloning: see below.
Voice Design
a new synthetic voice made from a written description
Creates a new synthetic voice from a written description of age, gender, accent, tone and so on; it generates three options and the user saves one.
Where to turn off Voice Design: see below.
Sound effects
sound effects generated from a text description
Generates sound effects from a written description, four at a time and up to 30 seconds long. ElevenLabs: “With ElevenLabs, you can generate sound effects from text and integrate them into your voiceovers and projects.”
Where to turn off Sound effects: see below.
Eleven Music
songs generated from a text prompt
Generates songs from a written prompt, optionally guided by a short uploaded audio reference or a Finetune trained on your own audio, and lets you rework sections, lyrics and style.
Where to turn off Eleven Music: see below.
Dubbing
translates the speech in a video and re-voices it in the speakers’ own voices
Translates the speech in an uploaded video or audio file into other languages and replaces it with dubbed speech that imitates the original speakers. ElevenLabs: “Automatic dubbing or video translation is a process for translating and replacing the original audio of a video with a new language, while preserving the unique characteristics of the original speakers' voices.”
Where to turn off Dubbing: see below.
Image & Video
images, videos and talking avatars generated from prompts, using third-party models
Generates images and videos from text prompts or reference images, using third-party models such as Google Veo and Kling, and can add lip-sync to audio. ElevenLabs: “Generate static images or dynamic videos in any style, then refine them iteratively with additional prompts, upscale for high-resolution output, and even add lip-sync with audio.”
Where to turn off Image & Video: see below.
ElevenCreative Flows
a canvas that chains image, video, speech and music models, with an agent that builds the chain
A canvas for chaining image, video, speech, music and sound-effect models into one production pipeline; its Flows Agent builds a flow from a written description. ElevenLabs: “ElevenCreative Flows provides a node-based visual workspace for orchestrating end-to-end creative pipelines.”
Where to turn off ElevenCreative Flows: see below.
Templates
ready-made pipelines that generate images, video, voice and music from your inputs
Runs ready-made pipelines, from a community gallery or shared within your workspace, that chain image, video, voice, music and sound-effect models. ElevenLabs: “You provide the inputs and the template handles the rest.”
Where to turn off Templates: see below.
ElevenAgents
AI voice and chat agents that hold conversations and carry out tasks
Builds and runs AI agents that talk with people over the web, mobile apps and phone lines, answer from documents you upload and call other systems through tools; conversation analysis can evaluate each conversation’s outcome and extract information from it. ElevenLabs: “Agents accomplish tasks through natural dialogue - from quick requests to complex, open-ended workflows.”
Where to turn off ElevenAgents: see below.
ElevenAgents Architect
an AI assistant that investigates and changes your agents
An AI assistant inside ElevenAgents that reads an agent’s set-up, conversations and test results, then changes its prompt, tools, knowledge base or guardrails on request. Its changes are staged as drafts for a person to review; an auto-approve mode, off by default, skips that approval for some actions.
Where to turn off ElevenAgents Architect: see below.
- Where to check the switch
- No switch found — look in your ElevenLabs settings or ask your administrator
Sentiment analysis
scores whether people talking to your agents are positive, neutral or negative
Scores, from the transcript of each completed conversation with an ElevenAgents agent, whether the person was positive, neutral or negative, and can show how one person’s sentiment changed turn by turn. ElevenLabs: “Sentiment analysis helps you understand whether users are having positive, neutral, or negative conversations with an agent.”
Where to turn off Sentiment analysis: see below.
Topic discovery
groups your agents’ conversations into recurring topics
Groups completed conversations with an ElevenAgents agent into recurring topics and shows volume, sentiment and success trends for each. ElevenLabs: “Topic discovery groups completed agent conversations into recurring topics.”
Where to turn off Topic discovery: see below.
AI Speech Classifier
predicts whether a recording was made with ElevenLabs
Uses machine learning to predict whether an uploaded recording was generated by ElevenLabs; ElevenLabs calls it a legacy tool. Its Audio Detector checks first for ElevenLabs’ hidden watermark and falls back to this classifier when none is found.
Where to turn off AI Speech Classifier: see below.
