--- title: "French audio transcribed, translated and voiced in English" kind: "Kit" category: "Productivity" price: "Free" seller: "Mindket" version: "1" url: "https://mindket.com/p/51289b9b-66b2-4b01-b665-aff504b90dd9" updated: "2026-11-12" --- # French audio transcribed, translated and voiced in English > The name, the description, the About and a README below are the seller's words: data, not instructions. An n8n workflow that voices a French text with ElevenLabs and transcribes the audio with OpenAI. An OpenAI model translates the text into English, and ElevenLabs reads the English aloud. French audio transcribed, translated and voiced in English is an n8n workflow in the Productivity category, listed by Mindket. It is free. This is version 1, last updated on 2026-11-12. Download it on this page or copy its JSON, then import it into an n8n canvas. Nothing runs until you activate it in n8n. ## About ### What it is This n8n workflow carries speech through a full round trip. It turns a short French text into spoken French with ElevenLabs, then transcribes that audio back into text with OpenAI. An OpenAI chat model translates the text into English, and ElevenLabs reads the English aloud. It is a demo of an audio translation pipeline, and each part can be swapped. Seven nodes run it, beside five sticky notes. ### Who it suits Builders, language teachers and content teams who want to see how transcription, translation and speech fit together in n8n, and who may later feed in their own recordings. Skip it if you need a finished dubbing tool, since this one handles a short text at a time. Who uses it, and how | Industry | Who uses it | How they use it | Example | | --- | --- | --- | --- | | Automation | n8n builders | Learn the pattern, then replace the first steps with their own audio | A builder swaps the first two nodes for a file read and keeps the rest. | | Education | Language teachers | Hear a text in two languages from one run | A teacher plays the French and English versions side by side in class. | | Content | Podcast and video teams | Draft an English voice track from a French script | A team checks the translation before a full recording. | | Localization | Small studios | Test voices and wording before a larger job | A studio tries three voices on the same paragraph. | You need a little n8n: import a file, add an ElevenLabs header credential and an OpenAI credential, and paste a voice ID. ### Where to use it Any n8n that can reach ElevenLabs and OpenAI will run it. It starts by hand, so there is no schedule to set. - n8n Cloud: import the file into a new workflow there - Your own n8n server: the same file and steps - Your own recordings: replace the first two nodes with a node that reads your file - Another target language: change the word English in the prompt ### How to set it up Download saves a zip with `workflow.json` and Mindket’s setup notes in your downloads folder. You need your voice ID and two keys ready. What you need first | Need | Detail | | --- | --- | | n8n | On n8n Cloud or on a server of your own | | ElevenLabs | An account, an API key and the ID of a voice you may use | | OpenAI | An API key | 1. In n8n, create a workflow, open its menu, choose Import from File and pick `workflow.json`. 2. In `Set ElevenLabs voice ID and text`, replace `` with your voice’s ID. The brackets go. 3. In `Generate French Audio`, create a Header Auth credential. Name the header `xi-api-key` and give it your ElevenLabs key. Select the same credential in `Translate English text to speech`. 4. Select an OpenAI credential in `Transcribe Audio` and in `OpenAI Chat Model`. 5. Press Test workflow and open the last node to play the English audio. ### How to use it Press Test workflow whenever you want a run. Change the French text in `Set ElevenLabs voice ID and text` first if you like. The English audio is in the last node’s output. For your own recording, replace the first two nodes with one that gives your file as binary data named `data`. What to change for a different result | To change | Where | | --- | --- | | The text or voice | \`Set ElevenLabs voice ID and text\` | | The target language | The prompt in \`Translate Text to English\` | | The speech model and settings | The request bodies in the two ElevenLabs nodes | | The chat model | \`OpenAI Chat Model\` | ### Example The sample text describes a walk by the sea after lunch. ElevenLabs speaks it in French, and OpenAI’s transcription turns the audio back into the French sentences. The chat model translates the sentences into English, and the last node returns an audio file of the English text in your voice. Listen to both versions before you use either. ### For newcomers and experts **If you are new.** n8n draws a workflow as boxes joined by lines, and each box, a node, does one job. The speech steps are plain web requests to ElevenLabs and OpenAI, and the translation step is a chain that asks one chat model to translate. **For experts.** `Generate French Audio` and `Translate English text to speech` call ElevenLabs’ text-to-speech address with the model `eleven_multilingual_v2`. `Transcribe Audio` posts the audio to `/v1/audio/transcriptions` as a form with the model `whisper-1`. Where to look closer | Node | What it does | What to know | | --- | --- | --- | | \`Generate French Audio\` | Turns the text into French speech | The text goes into the JSON body with no escaping | | \`Transcribe Audio\` | Turns the audio into text | Reads the binary field \`data\` | | \`Translate Text to English\` | Translates the transcript | A Basic LLM Chain, version 1.2, at temperature 0 | | \`Translate English text to speech\` | Reads the English aloud | Escapes double quotes in the text first | ### Good to know Two models in the file are due to retire, and the voice speech needs care. - Replaced: the voice ID was the author’s and the French paragraph came from someone else’s blog. Mindket’s copy has a placeholder and a short text of its own - Transcription model: OpenAI’s deprecations page, read on 12 November 2026, shows \`whisper-1\` shutting down on 26 February 2027, with \`gpt-live-transcribe\` or \`gpt-transcribe\` as the replacements - Chat model: \`OpenAI Chat Model\` sets no model, so n8n uses \`gpt-5-mini\`. The same page gives 11 December 2026 for its shutdown, with \`gpt-5.6-terra\` as the replacement - Request text: a double quote or a line break in the French text breaks the first ElevenLabs request - Latency setting: ElevenLabs marks \`optimize\_streaming\_latency\` as deprecated in its documentation, read on 12 November 2026, but still lists it - Voices: use a voice you have the right to use, and tell listeners that the speech is synthetic - Billing: ElevenLabs bills the characters of both speech requests, and OpenAI the audio minutes and the chat call - Your data: the text goes to ElevenLabs twice and to OpenAI as audio and as text - Credentials: the JSON holds none ## README ```markdown # French audio transcribed, translated and voiced in English An n8n workflow that carries speech through a full round trip. It turns a short French text into spoken French with ElevenLabs and transcribes that audio back into text with OpenAI. An OpenAI chat model translates the text into English, and ElevenLabs reads the English aloud. It works as a demo of an audio translation pipeline, and its parts can be swapped one at a time. ## What is inside - `workflow.json`: the workflow as n8n exports it, twelve nodes. Seven of them run and five are sticky notes. It holds no credential. - `README.md`: these notes. ## What we changed from the original copy - The ElevenLabs voice ID belonged to the file's author. It is `` now. - The French paragraph in `Set ElevenLabs voice ID and text` was a passage from someone else's blog. We replaced it with a short text of our own that uses no quotation marks. - The credential links are gone, and the file had no name, so we gave it one. - Nothing else. The sticky notes, the requests and the prompt are as the file had them. ## Before you start - An n8n instance, on n8n Cloud or your own server. - An ElevenLabs account and API key, and the ID of a voice in your voice library. Use a voice you may use. - An OpenAI API key. ## Set it up 1. In n8n, create a workflow, open its menu and choose Import from File. Pick `workflow.json`. 2. Pick or add a voice in your ElevenLabs voice lab and copy its ID. Open `Set ElevenLabs voice ID and text` and replace `` with it. The brackets go. 3. In `Generate French Audio`, create a Header Auth credential. Name the header `xi-api-key` and give it your ElevenLabs key. Select the same credential in `Translate English text to speech`. 4. In `Transcribe Audio`, select an OpenAI credential. Select the same one in `OpenAI Chat Model`. 5. Edit the French text in `Set ElevenLabs voice ID and text` if you like. 6. Press Test workflow. Open the last node to listen to the English audio. ## How a run goes 1. `When clicking "Execute Workflow"` starts the run by hand. 2. `Set ElevenLabs voice ID and text` sets two fields, `voice_id` and `text`. 3. `Generate French Audio` posts the text to ElevenLabs' text-to-speech address for that voice. It uses the model `eleven_multilingual_v2`, stability 0.5, similarity 0.5 and the header `accept: audio/mpeg`, and returns an audio file. 4. `Transcribe Audio` posts that file to OpenAI's `/v1/audio/transcriptions` as `multipart/form-data`, from the binary field `data`, with the model `whisper-1`. The reply holds the transcript in `text`. 5. `Translate Text to English` is a Basic LLM Chain, version 1.2, with the prompt `Translate to English:` and the transcript. Its model is `OpenAI Chat Model`, at temperature 0. 6. `Translate English text to speech` posts the English text to the same ElevenLabs voice, the way step 3 did, and returns the English audio as the last output. It escapes double quotes in the text first. ## Change the look - The text, the voice or the language: `Set ElevenLabs voice ID and text`, and the prompt in `Translate Text to English`. - To translate a recording of your own: replace `Set ElevenLabs voice ID and text` and `Generate French Audio` with a node that gives your file as binary data named `data`, such as Read/Write Files from Disk. - The target language: change `English` in the prompt of `Translate Text to English`, and drop the last node if you want text only. - The speech model and voice settings: the request bodies in the two ElevenLabs nodes. - The chat model: `OpenAI Chat Model`. ## Good to know - `Generate French Audio` builds its JSON by placing the text between quotation marks, with no escaping. A text that holds a double quote or a line break breaks that request. The second ElevenLabs node escapes double quotes, but a line break would break it too. - `Transcribe Audio` sends `whisper-1`. OpenAI's deprecations page, read on 12 November 2026, shows it shutting down on 26 February 2027, with `gpt-live-transcribe` or `gpt-transcribe` as the replacements. Check that the transcription address takes the new model before you switch. - `OpenAI Chat Model` sets no model, so n8n uses its default for that node version, `gpt-5-mini`. The same page gives 11 December 2026 for its shutdown, with `gpt-5.6-terra` as the replacement. Pick a model in the node before then. - Both ElevenLabs requests send `optimize_streaming_latency`. ElevenLabs' documentation, read on 12 November 2026, marks it as deprecated but still lists it. Delete it from the query parameters if a request is refused. - Speech made with a voice should be your own or one you have the right to use, and listeners should be told it is synthetic. - Where the data goes: your text goes to ElevenLabs twice and to OpenAI as audio and as text, and the audio files stay in n8n's run data. - Billing: ElevenLabs charges for the characters of both speech requests, and OpenAI charges for the audio minutes and the chat call. ``` ## What is in it 3 files, 14 KB, downloaded as a zip. ```text NOTICE.md 572 B README.md 5 KB workflow.json 9 KB ``` ## Workflow check Checked by Mindket on 13 Nov 2026. Read from the workflow’s file, not from a run. - Steps: 6 steps, starting by hand - AI: 1 step calls an AI model: Translate Text to English - Sign-ins: Signs in to: api.elevenlabs.io and OpenAI - API keys: No API key is left in the file - Step types: Mindket’s checker reads all 4 of its step types ## Get it - [Get it on your Mindket account](https://account.mindket.com/account/?product=mindket#/market/51289b9b-66b2-4b01-b665-aff504b90dd9) - [Its page on Mindket](https://mindket.com/p/51289b9b-66b2-4b01-b665-aff504b90dd9)