Nexra
All connectors
Implemented
Content creation & media
ElevenLabs logo

ElevenLabs

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

Turn approved scripts into voice-overs in content and training flows, then track character credits, history and Studio projects without leaving Nexra.

Build a flow with ElevenLabsProvider API documentation

Source actions

14

Destination actions

1

Data types

12

Validation status

Implemented · fixture tested.

Implementation is checked against provider-shaped fixtures for every action, authentication failures, rate limits, pagination and duplicate safety. Provider sandbox and authorised account validation are recorded separately when credential-backed runs are completed.

What you can map

default voice settings
  • Get default voice settings
    Source

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

    default_voice_settings.get
history
  • Get history item
    Source

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

    history.get
  • List generation history
    Source
    Incremental

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

    history.list
models
  • List models
    Source

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

    models.list
pronunciation dictionaries
  • List pronunciation dictionaries
    Source

    List pronunciation dictionaries that can be applied to speech generation.

    pronunciation_dictionaries.list
speech
  • Generate speech
    Destination
    Not retried automatically
    Approval before production

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

    speech.generate
studio chapters
  • List Studio chapters
    Source

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

    studio_chapters.list
studio projects
  • Get Studio project
    Source

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

    studio_projects.get
  • List Studio projects
    Source

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

    studio_projects.list
subscription
  • Get subscription and credits
    Source

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

    subscription.get
usage
  • Get workspace usage
    Source

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

    usage.list
user
  • Get user
    Source

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

    user.get
voice settings
  • Get voice settings
    Source

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

    voice_settings.get
voices
  • Get voice
    Source

    Get one voice's metadata and settings.

    voices.get
  • List voices
    Source

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

    voices.list

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. Nexra event triggers are not yet available; flows run on demand or on a schedule.

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.
  • The history-item-id response header is not listed in the OpenAPI document; it is captured when present. The character-cost header is documented in the API introduction (some examples show x-character-count, which is also read).
  • 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. Not yet verified on a live account.
  • 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.