Voice & audio · ElevenLabs
ElevenLabs
Turn text into natural speech, clone a voice, dub video into other languages, transcribe audio, and build voice agents.
Start here
- What this helps you do
- Narration, voiceover, dubbing and prototyping a voice agent, where you want studio-quality speech without a recording booth.
- What you leave with
- A practical way to use ElevenLabs on real work, plus the human checks before you rely on it.
- What to check before trusting it
- The use policy prohibits replicating another person's voice without consent or legal right, harmful impersonation and deceptive use. Keep the rights and consent evidence on file.
At a glance
- Version at last check
- Eleven v4 and v4 Turbo; earlier v3, Multilingual v2 and Flash models remain listed
- Category
- Voice & audio
- Pricing at last check
- Free tier, then paid plans from about US$6 (Starter) through Creator, Pro, Scale and Business to custom Enterprise, priced by monthly credits. Listed standard prices exclude taxes and temporary first-month promotions; products share the credit balance. Only paid plans carry a commercial licence.
What it does
Text to speech
Eleven v4 supports expressive speech and dialogue across 90-plus languages; v4 Turbo targets real-time delivery. Multilingual v2 remains available for long-form speech, and Flash v2.5 lists roughly 75 milliseconds of inference latency, excluding application and network time.
For work Narration, voiceover, audiobooks, phone systems and a consistent voice for a product or app.
Voice cloning
Clone a voice you have rights and consent to use, or design a new voice. The instant-cloning guide recommends 1-2 minutes of clear audio. Professional cloning requires verification and is limited to your own voice.
For work A single, consistent brand or creator voice used at scale across many pieces of content.
Dubbing
Translates a video or recording into other languages while re-synthesising the original speaker's own voice, matching their cadence, rather than replacing it with a generic one.
For work Localising courses, marketing videos and social content into new languages.
Speech to text (Scribe)
Transcription with speaker labelling (who said what) and word-level timestamps, across many languages.
For work Subtitles, captions, and meeting or interview transcripts.
Voice agents
Agents that listen and reply in real time across phone, chat and messaging apps in many languages, with analytics and workflow logic.
For work Support lines, booking and qualification calls handled by voice.
Music and sound effects
Generates music tracks and custom sound effects from a prompt. The pricing page lists music commercial use on paid plans; check the licence for the selected use.
For work Background music, jingles and sound design for video, podcasts and games.
Not for
Anything where using a real person's voice without their clear, recorded consent would be wrong, or where a synthetic voice must not be disclosed.
Real work with it
A small-business owner
Multilingual voiceover for a small business
- Write the script, or take an existing video you want in another language.
- Pick a library voice or clone your own, then generate the speech, or run Dubbing on the video.
- Export the audio and drop it into your video or phone system.
Human checkpoint Listen end to end for mispronounced product and brand names, and confirm a translation actually says what you mean before it goes out.
A teacher or course creator
Narrated lessons with captions
- Draft the lesson script.
- Generate narration in one consistent voice.
- Run Scribe over the audio to produce synced captions and a transcript.
Human checkpoint Proofread the auto-transcript for technical terms and names, and decide whether learners should be told the narration is AI.
The part that stays yours
A voice is someone's identity. Whose voice you may clone, getting consent on the record, disclosing that a voice is synthetic, and approving the script and tone are all human calls the tool does not make for you.
Plans and pricing (7)
Amounts recorded 17 October 2026. Confirm your region, billing period and current checkout before paying.
Free
US$0
Trying it out. No commercial licence.
Starter
US$6/mo
First paid step: commercial licence, instant cloning, dubbing.
Creator
US$22/mo
Serious creators: professional voice cloning, extra credits.
Pro
US$99/mo
Higher volume and higher-quality audio output via API.
Scale
US$299/mo
Small teams: seats and collaboration.
Business
US$990/mo
Larger teams: low-latency speech, more clones and seats.
Enterprise
Custom
Contracts, SSO, higher concurrency and support.
When to pick something else (3)
Descript
Your real job is editing a whole podcast or video, not just generating voice. Descript edits audio by editing text.
Murf
Compare the same short script in Murf and ElevenLabs, including editing effort, pronunciation and the terms for your use.
OpenAI or Google TTS
Compare speech generation in the provider stack you already use, including cost, voice options and implementation effort.
Watch-outs (5)
- The use policy prohibits replicating another person's voice without consent or legal right, harmful impersonation and deceptive use. Keep the rights and consent evidence on file.
- The use policy requires clear disclosure when required by law or when withholding it would materially mislead people. Do not conceal provenance signals to disguise generated content.
- Do not assume a generated voice is anonymous or that provenance detection will catch every misuse; keep your own approval and rights records.
- Credits are charged in different units for text, transcription and dubbing. Estimate the actual workload using the current rate table; dubbing can consume a plan quickly.
- Free-tier output is not licensed for commercial use; check the applicable terms before publishing and use a paid plan for commercial work.