ToolsCompaniesAbout

ElevenAPI

by ElevenLabs@elevenlabsLondon, United KingdomNo ratings yet

Developer API for text to speech, transcription, music, sound effects, dubbing and voice agents.

Visit elevenlabs.io
Tool type
Developer API for AI audio models
Made for
Developers and product teams building audio features
Runs on
REST API and application SDKs
The developer console is used for key creation and setup; runtime calls are made from your app or server, not from the console.
Last checked
28 Oct 2026
3 product sources

What it does

ElevenAPI is a developer interface to ElevenLabs audio models. Developers send text, audio or prompts and receive generated speech, transcripts, music, sound effects, dubbed audio or voice-agent sessions. Requests authenticate with an API key sent in the xi-api-key header, and official Python and TypeScript SDKs wrap the REST endpoints.

Teams use it to build content localization and dubbing pipelines, automated video narration, conversational voice interfaces, accessibility tools and training audio. The API supports both streaming and batch processing, and Text to Speech and Speech to Text both offer streaming output. Voices can be referenced by ID from a library that includes cloned and designed voices.

It suits developers and product teams building audio into applications. Access requires an ElevenLabs account and an API key, and usage is metered and billed in US dollars, with pay-as-you-go available from the Starter plan. Limits vary by plan and endpoint, and music generation carries additional licensing requirements for advertising, film, TV, games and enterprise distribution.

What it can do

  • Text to speech with audio tags and streaming output, billed per character
  • Speech to text transcription, realtime or batch, billed per audio hour
  • Music generation from text prompts with a 5-minute duration limit on the pricing page
  • Sound effect generation from text descriptions
  • Dubbing that translates and voices audio or video, with automatic speaker detection
  • Voice design, cloning and voice changing from a library of voices referenced by ID

Works with

  • Python SDK (elevenlabs package)
  • TypeScript SDK
  • Flutter, Swift and Kotlin SDKs for the Agents platform (per FAQ)

Example workflows

Localized video narration
Inputs: a source video and a target language. Steps: submit the video to the Dubbing API, poll or receive the dubbed output, then download the translated audio track. Output: a dubbed audio or video file in the target language, billed per source audio minute.
Realtime voice reply in an app
Inputs: user text and a voice ID from the library. Steps: send text to the Text to Speech endpoint with streaming enabled, then play the audio chunks as they arrive. Output: spoken audio that begins playing before the full file is generated, billed per character.

Before you choose

  • Pricing is metered per product and billed in USD: Text to Speech per character, Speech to Text per audio hour, Music and Sound Effects per generation or minute, and Dubbing per source audio minute. Check the rate table on the pricing page for the specific model you use.
  • Music output requires an additional commercial license for advertising, film, TV, games and enterprise distribution, according to the FAQ.
  • Usage limits and concurrency vary by plan and endpoint; the Agents platform bills connected audio above your concurrency limit at burst rates.

Listed under

Get started

Create an API key in the dashboard, store it as ELEVENLABS_API_KEY, install the SDK and run a sample request. The CLI onboarding command can automate this.

  1. Create an API key in the ElevenLabs dashboard and store it in a .env file as ELEVENLABS_API_KEY, keeping the file out of version control.
  2. Install the official SDK for your language: pip install elevenlabs for Python, or the TypeScript SDK for Node projects.
  3. Run a first text-to-speech request using a voice ID from the library, and install MPV or ffmpeg if you want audio to play through your speakers.
Get an API key and make a first request

Plans and prices

Prices in USD

API usage is billed in US dollars, not credits, per the pricing FAQ. Pay-as-you-go is available from the Starter plan. Start for free is offered on the pricing page; Startup Grants offer 12 months free to eligible startups. Per-product rates are listed on the pricing page.

Pay as you goUsage-basedNamed meter: Text to Speech characters. Rates for other meters (Speech to Text per hour, Music per minute, Dubbing per minute) are in the pricing page rate table.
  • No commitment, cancel anytime
  • Pay only for what you use

Source: elevenlabs.io/pricing/api, checked 28 Oct 2026. Prices can change; check before you buy.

Sources for this overview

Product pages, documentation, and pricing checked 28 Oct 2026. Each source supports part of the overview; availability and prices can change.

Ratings and reviews

No ratings for ElevenAPI yet.

Be the first to rate it

What’s changed

Free account

See what’s changed at ElevenAPI

Launches, price moves and pivots, each with a date and a source. Free with an account.

Signals

Free account

See ElevenAPI’s signals

Launch traction, hiring and release activity, tracked over time. Free with an account.

Data and security

Free account

See how ElevenAPI handles your data

Training on your files, compliance, hosting and the models behind it. Free with an account.

Compare with similar tools

Free account

Compare ElevenAPI side by side

Prices, platforms and features against similar tools, with sources. Free with an account.

Where this comes from

How we research
Company website
elevenlabs.io: product, pricing and policy pages
Web search
Confirms the official site
Social accounts
Accounts the company links, and its posts on X
Human review
Checked by a person
knowledge_base

Last checked 28 Oct 2026. Every field keeps its source and date; unknown means we couldn’t confirm it.