{ "id": "hbkFf6ejMdbXXP5Y", "name": "4. Generate High-Quality Audio with Voxtral Small 24B 2507", "tags": [], "nodes": [ { "id": "2a642053-9e2a-4470-802c-e0e659161b5b", "name": "On clicking 'execute'", "type": "n8n-nodes-base.manualTrigger", "position": [ 176, -640 ], "parameters": {}, "typeVersion": 1 }, { "id": "165e01ed-cb50-4bbd-b23b-9b2e748540f6", "name": "Set API Key", "type": "n8n-nodes-base.set", "position": [ 400, -640 ], "parameters": { "options": {}, "assignments": { "assignments": [ { "id": "64cd57c7-2224-48a6-88df-c37b310f8eb3", "name": "replicate_api_key", "type": "string", "value": "YOUR_REPLICATE_API_KEY" } ] } }, "typeVersion": 3.3 }, { "id": "ba28ca28-3400-40aa-a45f-307dcb1e290f", "name": "Create Prediction", "type": "n8n-nodes-base.httpRequest", "position": [ 672, -640 ], "parameters": { "url": "https://api.replicate.com/v1/predictions", "method": "POST", "options": { "timeout": 60000 }, "jsonBody": "{\n \"version\": \"31b40d9229c3df8c13863fcdd8cc95e6c1c6eb2b6c653936934234eadcc23d41\",\n \"input\": {\n \"audio\": \"https://example.com/input.audio\",\n \"max_new_tokens\": 1024\n }\n}", "sendBody": true, "sendHeaders": true, "specifyBody": "json", "authentication": "genericCredentialType", "genericAuthType": "httpHeaderAuth", "headerParameters": { "parameters": [ { "name": "Authorization", "value": "={{ 'Bearer ' + $('Set API Key').item.json.replicate_api_key }}" }, { "name": "Content-Type", "value": "application/json" } ] } }, "typeVersion": 4.2 }, { "id": "6608458d-91a3-49f8-81d9-f35469106db1", "name": "Extract Prediction ID", "type": "n8n-nodes-base.code", "position": [ 928, -640 ], "parameters": { "mode": "runOnceForEachItem", "jsCode": "// Extract prediction ID and initial status\\nconst prediction = $input.item.json;\\nconst predictionId = prediction.id;\\nconst initialStatus = prediction.status;\\n\\n// Store the prediction ID for polling\\nreturn {\\n predictionId: predictionId,\\n status: initialStatus,\\n predictionUrl: `https://api.replicate.com/v1/predictions/${predictionId}`\\n};" }, "typeVersion": 2 }, { "id": "e2177196-1246-4051-9e61-783e21bc6197", "name": "Wait", "type": "n8n-nodes-base.wait", "position": [ 1152, -640 ], "parameters": { "unit": "seconds", "amount": 2 }, "typeVersion": 1 }, { "id": "4adcc795-860d-4fd4-ab09-b57966ae765f", "name": "Check Prediction Status", "type": "n8n-nodes-base.httpRequest", "position": [ 1376, -640 ], "parameters": { "url": "={{ $json.predictionUrl }}", "options": {}, "sendHeaders": true, "authentication": "genericCredentialType", "genericAuthType": "httpHeaderAuth", "headerParameters": { "parameters": [ { "name": "Authorization", "value": "={{ 'Bearer ' + $('Set API Key').item.json.replicate_api_key }}" } ] } }, "typeVersion": 4.2 }, { "id": "1721a07e-3db6-44c3-b5ae-acdd781d5367", "name": "Check If Complete", "type": "n8n-nodes-base.if", "position": [ 1600, -640 ], "parameters": { "conditions": { "boolean": [ { "value1": "={{ $json.status }}", "value2": "succeeded" } ] } }, "typeVersion": 1 }, { "id": "3de7fe83-762e-4d28-8e92-aee96e19d0f2", "name": "Process Result", "type": "n8n-nodes-base.code", "position": [ 1872, -752 ], "parameters": { "mode": "runOnceForEachItem", "jsCode": "// Process the completed prediction\\nconst result = $input.item.json;\\n\\nreturn {\\n status: result.status,\\n output: result.output,\\n metrics: result.metrics,\\n created_at: result.created_at,\\n completed_at: result.completed_at,\\n model: 'notdaniel/voxtral-small-24b-2507',\\n audio_url: result.output\\n};" }, "typeVersion": 2 }, { "id": "cde9ca87-7473-4c18-96db-fb907b6b9213", "name": "Sticky Note", "type": "n8n-nodes-base.stickyNote", "position": [ 128, -1008 ], "parameters": { "color": 7, "width": 406, "height": 543, "content": "## \u26a1 Section 1: Trigger & Authentication\n\n* **\ud83d\udd18 On clicking 'execute'** \u2192 Manually starts the workflow.\n* **\ud83d\udd11 Set API Key** \u2192 Stores your Replicate API key to authenticate requests.\n\n**Benefit:** Securely connects your workflow to Replicate\u2019s API and ensures only authorized requests are made.\n\n---\n\n" }, "typeVersion": 1 }, { "id": "89b11241-3f2d-4458-8562-ea5bde49d8ac", "name": "Sticky Note1", "type": "n8n-nodes-base.stickyNote", "position": [ 560, -1104 ], "parameters": { "color": 6, "width": 326, "height": 639, "content": "## \ud83c\udf9b\ufe0f Section 2: Create Prediction\n\n* **\ud83c\udf10 Create Prediction** \u2192 Sends a request to Replicate\u2019s API with parameters like:\n\n * **audio**: Input audio file (e.g., a reference sample).\n * **max\\_new\\_tokens**: Maximum number of tokens to generate (controls audio length/complexity).\n\n**Benefit:** Starts the audio generation process with configurable input and settings.\n\n---" }, "typeVersion": 1 }, { "id": "b953d5d4-99b1-42d7-98ea-b71ca330510c", "name": "Sticky Note2", "type": "n8n-nodes-base.stickyNote", "position": [ 912, -1056 ], "parameters": { "color": 3, "width": 822, "height": 591, "content": "## \u23f3 Section 3: Polling & Status Tracking\n\n* **\ud83c\udd94 Extract Prediction ID** \u2192 Captures the unique prediction ID and endpoint for polling.\n* **\u23f1\ufe0f Wait** \u2192 Pauses for 2 seconds before re-checking.\n* **\ud83d\udce1 Check Prediction Status** \u2192 Polls Replicate\u2019s API to see if the audio generation is done.\n* **\u2705 Check If Complete** \u2192\n\n * If finished: moves forward to process results.\n * If not: loops back to wait and check again.\n\n**Benefit:** Efficiently manages asynchronous audio generation, ensuring the workflow only proceeds when results are ready.\n\n---\n\n" }, "typeVersion": 1 }, { "id": "334b4b5c-eb1e-4685-8a0d-e907442cc11d", "name": "Sticky Note3", "type": "n8n-nodes-base.stickyNote", "position": [ 1760, -1184 ], "parameters": { "color": 5, "width": 326, "height": 719, "content": "## \ud83c\udfa7 Section 4: Process Result\n\n* **\ud83d\udcdd Process Result** \u2192 Extracts and structures final output data:\n\n * **status** (success or failure)\n * **output** (raw response)\n * **metrics** (generation statistics)\n * **timestamps** (created and completed times)\n * **audio\\_url** (final generated audio link)\n\n**Benefit:** Provides a clean, structured output that can be used in follow-up automations (e.g., sending audio to users, storing in a database, or sharing via email).\n\n---\n\n" }, "typeVersion": 1 }, { "id": "0a692527-c66c-4cb3-8a5c-97b589cc536b", "name": "Sticky Note9", "type": "n8n-nodes-base.stickyNote", "position": [ -1712, -1120 ], "parameters": { "color": 4, "width": 1300, "height": 320, "content": "=======================================\n WORKFLOW ASSISTANCE\n=======================================\nFor any questions or support, please contact:\n Yaron@nofluff.online\n\nExplore more tips and tutorials here:\n - YouTube: https://www.youtube.com/@YaronBeen/videos\n - LinkedIn: https://www.linkedin.com/in/yaronbeen/\n=======================================\n" }, "typeVersion": 1 }, { "id": "578ed070-c0ee-4df5-a4e9-124f7609d7c1", "name": "Sticky Note4", "type": "n8n-nodes-base.stickyNote", "position": [ -1712, -784 ], "parameters": { "color": 4, "width": 1289, "height": 1758, "content": "# Generate High-Quality Audio with Voxtral Small 24B 2507\n\nThis workflow integrates the **notdaniel/voxtral-small-24b-2507** model from Replicate to generate audio content from provided inputs. It handles API authentication, creates predictions, polls until completion, and outputs the final generated audio file.\n\n---\n\n## \u26a1 Section 1: Trigger & Authentication\n\n* **\ud83d\udd18 On clicking 'execute'** \u2192 Manually starts the workflow.\n* **\ud83d\udd11 Set API Key** \u2192 Stores your Replicate API key to authenticate requests.\n\n**Benefit:** Securely connects your workflow to Replicate\u2019s API and ensures only authorized requests are made.\n\n---\n\n## \ud83c\udf9b\ufe0f Section 2: Create Prediction\n\n* **\ud83c\udf10 Create Prediction** \u2192 Sends a request to Replicate\u2019s API with parameters like:\n\n * **audio**: Input audio file (e.g., a reference sample).\n * **max\\_new\\_tokens**: Maximum number of tokens to generate (controls audio length/complexity).\n\n**Benefit:** Starts the audio generation process with configurable input and settings.\n\n---\n\n## \u23f3 Section 3: Polling & Status Tracking\n\n* **\ud83c\udd94 Extract Prediction ID** \u2192 Captures the unique prediction ID and endpoint for polling.\n* **\u23f1\ufe0f Wait** \u2192 Pauses for 2 seconds before re-checking.\n* **\ud83d\udce1 Check Prediction Status** \u2192 Polls Replicate\u2019s API to see if the audio generation is done.\n* **\u2705 Check If Complete** \u2192\n\n * If finished: moves forward to process results.\n * If not: loops back to wait and check again.\n\n**Benefit:** Efficiently manages asynchronous audio generation, ensuring the workflow only proceeds when results are ready.\n\n---\n\n## \ud83c\udfa7 Section 4: Process Result\n\n* **\ud83d\udcdd Process Result** \u2192 Extracts and structures final output data:\n\n * **status** (success or failure)\n * **output** (raw response)\n * **metrics** (generation statistics)\n * **timestamps** (created and completed times)\n * **audio\\_url** (final generated audio link)\n\n**Benefit:** Provides a clean, structured output that can be used in follow-up automations (e.g., sending audio to users, storing in a database, or sharing via email).\n\n---\n\n## \ud83d\udcca Workflow Overview\n\n| Section | Purpose | Key Nodes | Benefit |\n| --------------------------- | ------------------------------- | ----------------------------------------------------------------------- | -------------------------------- |\n| \u26a1 Trigger & Authentication | Start workflow & authenticate | Manual Trigger, Set API Key | Secure execution |\n| \ud83c\udf9b\ufe0f Create Prediction | Submit audio generation request | Create Prediction | Start model processing |\n| \u23f3 Polling & Status Tracking | Monitor prediction progress | Extract Prediction ID, Wait, Check Prediction Status, Check If Complete | Ensures reliable completion |\n| \ud83c\udfa7 Process Result | Format and deliver output | Process Result | Clean audio result ready for use |\n\n---\n\n## \u2705 Final Benefits\n\n* \ud83d\udd12 Secure authentication with Replicate\n* \ud83c\udf9b\ufe0f Flexible audio generation using **voxtral-small-24b-2507**\n* \u23f3 Reliable polling until results are ready\n* \ud83c\udfa7 Clean and structured audio output\n\n---\n" }, "typeVersion": 1 } ], "active": false, "settings": { "executionOrder": "v1" }, "versionId": "9fba5d71-252a-4d19-91f1-0ffbab4f47ab", "connections": { "Wait": { "main": [ [ { "node": "Check Prediction Status", "type": "main", "index": 0 } ] ] }, "Set API Key": { "main": [ [ { "node": "Create Prediction", "type": "main", "index": 0 } ] ] }, "Check If Complete": { "main": [ [ { "node": "Process Result", "type": "main", "index": 0 } ], [ { "node": "Wait", "type": "main", "index": 0 } ] ] }, "Create Prediction": { "main": [ [ { "node": "Extract Prediction ID", "type": "main", "index": 0 } ] ] }, "Extract Prediction ID": { "main": [ [ { "node": "Wait", "type": "main", "index": 0 } ] ] }, "On clicking 'execute'": { "main": [ [ { "node": "Set API Key", "type": "main", "index": 0 } ] ] }, "Check Prediction Status": { "main": [ [ { "node": "Check If Complete", "type": "main", "index": 0 } ] ] } } }