Skip to content
Start in the sandbox
All connectors
ElevenLabs logo

ElevenLabs

Content creation & media

Move briefs, assets and sign-offs through ElevenLabs without chasing between tools.

14 ways to read, 1 way to write, each write switched on by you.

Try this in the sandboxBring us a workflow

Quality checks

Built and tested with example responses.

  1. Ready to connect: doneEvery listed action is built in.
  2. Built and tested with example responses: doneEach action is built from the provider’s published API and tested against example responses, errors, rate limits and paging.
ElevenLabs with Nexra

Connected, approved, proven.

The things teams do most with ElevenLabs, an example flow with a person in the loop, and what Nexra keeps as proof.

Top actions

  • Generate speechspeech.generateApproval by rule
  • List generation historyhistory.listRead

Example flow

  1. ElevenLabs · List generation historyhistory.listDone
  2. ElevenLabs · Generate speechspeech.generateMaker-checker
  3. Nexra · Record the decision and result in the evidence chainProven

Example workflow. Routine runs go through on their own. Only a change your rules flag, such as one over a limit you set, waits for the right person, who sees the exact change and the rule before it reaches ElevenLabs.

What gets logged

  • Whether it ran on its own or who approved it, and under which rule
  • A fingerprint of the exact request sent to ElevenLabs
  • ElevenLabs's reply: what it created or changed
  • One entry in the evidence chain, linked to the one before

Try this in the sandbox

Run the whole flow with test data in your sandbox, then connect your own account when you are ready to go live.

Try this in the sandboxBring us a workflow

For developers

Technical detail

Read ElevenLabs voices, models, generation history, Studio projects, subscription and usage, and generate speech from text (billable, metadata only).

ElevenLabs API docs
Source actions
14
Destination actions
1
Data types
12

What you can map

Reads are always available. Writes are off until you switch them on for a connection, and governed writes follow your policies.

default voice settings1
  • Get default voice settingsSource

    Get the default voice settings applied when a request does not override them.

history2
  • Get history itemSource

    Get one generated speech item's metadata, text, voice, model and characters used.

  • List generation historySourceIncremental

    List generated speech items (metadata only), newest first, filtered by voice, model, source or creation date.

models1
  • List modelsSource

    List the speech models with their capabilities, languages and per-request character limits.

pronunciation dictionaries1
  • List pronunciation dictionariesSource

    List pronunciation dictionaries that can be applied to speech generation.

speech1
  • Generate speechDestinationNot retried automaticallyApproval before production

    Convert text to speech with a voice and model. Billable: consumes character credits. Returns generation metadata; the audio stays in ElevenLabs history.

studio chapters1
  • List Studio chaptersSource

    List a Studio project's chapters with conversion progress and state.

studio projects2
  • Get Studio projectSource

    Get one Studio project's settings, state and chapter count.

  • List Studio projectsSource

    List Studio (long-form audio and video) projects and their conversion state.

subscription1
  • Get subscription and creditsSource

    Get the subscription tier, character credits used and remaining, reset date and voice slots.

usage1
  • Get workspace usageSource

    Get credit and character usage over time for the workspace, bucketed by the chosen interval.

user1
  • Get userSource

    Get the API key owner's user and workspace IDs, seat type and subscription tier.

voice settings1
  • Get voice settingsSource

    Get a voice's stability, similarity, style, speaker boost and speed settings.

voices2
  • Get voiceSource

    Get one voice's metadata and settings.

  • List voicesSource

    List voices available to the account, with search, type, category and sort filters.

Access and limits

Authentication
ElevenLabs API key (xi-api-key header)
Plans and access
All ElevenLabs plans, including Free, can use the API. Character credits, voice slots, concurrency and output formats depend on the plan. API keys can be limited to specific endpoints, a credit quota and IP addresses. A key restricted from an endpoint returns HTTP 401 or 403. Data-residency workspaces (EU, India, Singapore) must use their own API host.
Test environment
There is no separate sandbox. Use a Free plan account with its monthly character allowance for testing; every generation consumes real credits.
Rate limits
ElevenLabs limits concurrent requests by plan and returns HTTP 429 with code rate_limit_exceeded or concurrent_limit_exceeded. Nexra backs off on reads; text-to-speech is billable and is never retried automatically.
Pagination
Voices (v2) and pronunciation dictionaries use a page token (next_page_token / next_cursor) while has_more is true. History pages with start_after_history_item_id set to last_history_item_id. Models, Studio projects and chapters are single lists.
Provider events
ElevenLabs webhooks cover asynchronous products such as agent post-call events; text-to-speech is synchronous and has no completion webhook. Flows run on demand, on a schedule, or when a scheduled check finds new or changed records.

Before you build a flow

  • Generate speech returns metadata only (request ID, history item ID when ElevenLabs sends it, character cost and content type). The audio file is a binary download, which the Connect engine does not carry; fetch it from ElevenLabs history in the app. Binary upload and download is an engine gap.
  • Generate speech is billable: every call consumes character credits. It is never retried automatically and has no idempotency key, so a timed-out request may still have been charged; check History before repeating it.
  • Output is limited to low-bitrate MP3 (32 to 64 kbps) and text to 5,000 characters, so a generation stays within the engine's 5 MB response limit. Higher-quality, PCM, WAV and Opus formats are not offered.
  • Excluded by design: instant and professional voice cloning (needs voice samples and the speaker's consent), voice design and remixing, speech-to-speech, dubbing, sound effects, music, conversational agents, and Studio project creation, conversion or editing. No deletes of voices, history items, projects or dictionaries.
  • Get workspace usage uses POST /v1/workspace/analytics/query/usage-by-product-over-time, which returns a generic column/row table; group_by and filters are not exposed because their value shapes are not documented in detail.
  • History search text is sent in the URL, so email addresses are refused. History has no updated-since filter; Nexra uses date_after_unix (creation time).
  • Personal account fields (first name, API key preview, referral links, invoices and payment details) are never mapped from the user and subscription responses.

Developer reference

  1. Create the ElevenLabs credentials described above with the narrowest permissions your flows need.
  2. In Nexra, open Connect, then Connections, then New connection, choose ElevenLabs, enter its settings and credentials, and tick only the write actions you need. Connection guide
  3. Test the connection, then use its actions as flow sources and destinations. Flow guide
ElevenLabs docsAPI referenceElevenLabs docsAuthenticationElevenLabs docsRate limits

Machine-readable detail: GET /api/public/connect/connectors/elevenlabs and the Connections API.