ceven

ElevenLabs

Turns your text assets into high fidelity audio and dubbed video across any language, automating the production of voiceovers and localized content for your digital channels.

Try ElevenLabs in Ceven

Ask Ceven anything
Standard

Why use Ceven?

  1. AI native ElevenLabs integration

    • Describe the outcome and Ceven picks the right ElevenLabs calls, fills the parameters, and checks the result.
    • Structured, agent friendly tool schemas so each call runs reliably instead of by guesswork.
    • Rich coverage for reading, writing, and querying your ElevenLabs data, across all 155 of its actions.

  2. Managed auth

    • Built in OAuth with automatic token refresh and rotation.
    • One place to manage, scope, and revoke ElevenLabs access.
    • Per user and per environment credentials instead of shared keys.

  3. Agent optimized design

    • Actions are tuned from real success and error rates so reliability climbs over time.
    • Full execution logs so you always know what ran in ElevenLabs, when, and on whose behalf.
    • The agent pauses and asks when ElevenLabs is unclear instead of plowing ahead.

  4. Enterprise grade security

    • Fine grained access so you control which agents and people can reach ElevenLabs.
    • Least privilege by default, read scopes first and only the writes a workflow needs.
    • A full audit trail of every ElevenLabs action to support review and sign off.

Supported tools

Every action Ceven's agents can run on ElevenLabs, and when to use it.

Text to speech
Use this when you need to convert a block of text into a downloadable audio file using a specific voice and model.
Dub video or audio
Translate a video or audio file into a target language while preserving the original speaker characteristics.
Add a voice
Upload audio samples to initiate the process of cloning a custom voice for future synthesis.
Edit voice settings
Adjust stability, similarity enhancement, and style exaggeration to fine tune how a voice sounds.
Create project
Start a new studio project for long form content like audiobooks, initializing it with a name and source content.
Convert project to speech
Trigger the full conversion of a studio project and all its chapters into final audio files.
Get generated items
Pull a list of previously generated audio files from history, including metadata and voice IDs.
Add pronunciation rules
Define custom aliases or phonemes in a dictionary to ensure the AI says specific words correctly.
Get models
Pull the list of available text to speech models and their specific language capabilities.
Get project details
Retrieve the full state of a project including chapter status and conversion progress.
Delete voice
Permanently remove a custom cloned voice from the account library using its unique ID.
Get audio from history
Retrieve the actual audio file for a specific generation event using the history item ID.
Add a pronunciation dictionary from file
Adds a new pronunciation dictionary from a lexicon file to improve speech synthesis accuracy.
Add new project with attributes
Use to create a new elevenlabs project for text to speech synthesis (e.g., audiobooks); a project `name` is required by the api for creation, and content can be initialized using `from url` or `from document`.
Add rules to the pronunciation dictionary
Adds one or more custom pronunciation rules (alias or phoneme) to an existing pronunciation dictionary.
Add sharing voice
Adds an existing, shareable voice to a specified user's elevenlabs account library under a new custom name, requiring the user's public id and the voice id.
Convert chapter to audio
Converts the textual content of a chapter, identified by `chapter id` within a `project id`, into audio format.
Convert a project
Converts an existing elevenlabs studio project, including all its chapters and using its configured settings and voices, into speech.
Create a previously generated voice
Finalizes the creation of a voice using its `generated voice id` from a previous generation step by assigning a name, description, and optional labels.
Create an AudioNative enabled project
Creates an elevenlabs audionative project, generating an embeddable audio player from a provided content file using text to speech, allowing customization of player appearance, audio settings, and conversion options.
Delete chapter from project
Irreversibly deletes a specific, existing chapter from an existing project, typically to remove unwanted or obsolete content.
Delete a dubbing project
Permanently deletes a dubbing project by its id; this action is irreversible and the project cannot be recovered.
Delete history item
Permanently deletes a specific history item (including its audio file and metadata) using its `history item id`; this operation is irreversible and should be used with caution.
Delete project by id
Use to irreversibly delete a specific project by its `project id`; the project must exist and be accessible, and this action cannot be undone.
Delete voice sample
Permanently deletes a specific voice sample for a given voice id; this action is irreversible.
Delete voice by id
Permanently and irreversibly deletes a specific custom voice using its `voice id`; the voice must exist and the authenticated user must have permission to delete it.
Download history items
Downloads audio clips from history by id(s), returning a single file or a zip archive, with an optional output format (e.g., 'wav'); provides only audio content, no metadata.
Dub a video or an audio file
Dub a video or audio file into a specified target language, requiring 'file' or 'source url', 'target lang', and 'csv file' if 'mode' is 'manual'.
Edit voice
Updates the name, audio files, description, or labels for an existing voice model specified by `voice id`.
Text to speech stream
Converts text to a spoken audio stream, allowing latency optimization, specific output formats (some tier dependent), and custom pronunciations; ensure the chosen model supports text to speech and text is preferably under 5000 characters.

30 actions · scroll to see them all

Frequently asked questions

Ceven interacts with the ElevenLabs voice cloning API by uploading your provided audio samples and assigning a name to the new voice. It is important to note that the voice is not immediately usable for synthesis the second the request is sent. There is a short processing window where ElevenLabs analyzes the samples to build the voice model. Ceven monitors the status of the voice creation and will notify the workflow once the voice ID is active and ready for text to speech tasks. You can manage these voices later by updating their labels or deleting them entirely through the Ceven interface.
Yes. Ceven can manage ElevenLabs pronunciation dictionaries for you. You can use the workflow to add specific rules for how a brand name or a complex technical term should be spoken. This is done by sending the word and its corresponding phoneme or alias to the dictionary API. Once the rule is set, any subsequent text to speech calls using that dictionary will apply the custom pronunciation. This prevents the AI from mispronouncing niche terminology in professional recordings or technical tutorials, ensuring your brand sounds polished and accurate across all generated audio.
The dubbing process begins when you provide a source URL or file and a target language. Ceven sends this to ElevenLabs, which then analyzes the original speech, translates the text, and synthesizes new audio that matches the original timing and tone. For high precision needs, you can provide a CSV file for manual translation overrides. Ceven then tracks the dubbing project metadata to see when the process is complete. Once finished, the agent can pull the dubbed audio file or the full video and save it to your cloud storage or CMS.
ElevenLabs operates on a character quota system based on your subscription tier. When a workflow attempts to generate audio that exceeds your remaining balance, the ElevenLabs API returns a specific error indicating insufficient quota. Ceven captures this error and can be configured to trigger a notification to the account owner or pause the workflow until the quota resets or is upgraded. Because character usage is billed per single character generated, it is a good practice to use Ceven to trim your source text before sending it to the synthesis engine.
Yes, ElevenLabs imposes limits on the number of custom voices you can have in your library, and these limits vary significantly by your subscription tier. Free and starter tiers have much tighter constraints than the professional or enterprise tiers. If you reach your limit, the API will reject requests to add new voices. Ceven can help you manage this by listing your current voices and identifying old or unused clones that can be deleted to make room for new ones, ensuring your production pipeline does not grind to a halt.
Ceven uses the ElevenLabs Studio projects feature for long form content. Instead of a single text to speech call, which has character limits, the agent creates a project and breaks the content into chapters. It then manages the conversion of each chapter individually. This allows for much finer control over the pacing and tone of a long recording. Ceven can check the conversion status of each chapter and only trigger the final project export once every section has been successfully processed into audio, making it ideal for books or long podcasts.
Ceven acts as a secure bridge between your storage and ElevenLabs. When you initiate a voice clone, the audio samples are transmitted directly to ElevenLabs via an encrypted API call. We do not store your raw audio samples on our own servers longer than is necessary to complete the transfer. The resulting voice model resides within your ElevenLabs account, and access is governed by the API key you provided. You maintain full ownership of the voice and can delete the voice and its associated samples at any time via the manage voice actions.
ElevenLabs offers several models, such as Multilingual v2, which supports a wide array of languages and high emotional range. Ceven can pull a real time list of all available models using the get models action. The choice depends on your needs. If you are doing a simple English voiceover, a standard model might be faster, but for global dubbing or highly nuanced storytelling, the Multilingual models are superior. You can set the default model at the workflow level or allow the agent to choose based on the target language of the content.

Alternatives to ElevenLabs

Other tools that solve a similar problem. Ceven supports these too, so you can switch or run more than one at once.

PlayHT logoPlayHTLovo logoLovoMurf logoMurf

Try Ceven on your stack

Plug Ceven on top of the tools you already run. Connect ElevenLabs and the rest of your stack, describe the outcome, and its agents handle the work end to end, days of it in minutes.

Get started for free