# Audio Transcriber (`parseforge/audio-transcriber`) Actor Automates audio transcription from multiple sources (files or links). Normalizes input format to ensure optimal processing. Generates word-for-word transcriptions maintaining references to source audio, perfect for datasets requiring traceability and regulatory compliance. - **URL**: https://apify.com/parseforge/audio-transcriber.md - **Developed by:** [ParseForge](https://apify.com/parseforge) (community) - **Categories:** AI, Developer tools, Other - **Stats:** 113 total users, 23 monthly users, 100.0% runs succeeded, 0 bookmarks - **User rating**: 5.00 out of 5 stars ## Pricing Pay per event This Actor is paid per event. You are not charged for the Apify platform usage, but only a fixed price for specific events. Since this Actor supports Apify Store discounts, the price gets lower the higher subscription plan you have. Learn more: https://docs.apify.com/platform/actors/running/actors-in-store#pay-per-event ## What's an Apify Actor? Actors are a software tools running on the Apify platform, for all kinds of web data extraction and automation use cases. In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours, and optionally produces a well-defined JSON output, datasets with results, or files in key-value store. In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server. Actors are written with capital "A". ## How to integrate an Actor? If asked about integration, you help developers integrate Actors into their projects. You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready. The best way to integrate Actors is as follows. In JavaScript/TypeScript projects, use official [JavaScript/TypeScript client](https://docs.apify.com/api/client/js.md): ```bash npm install apify-client ``` In Python projects, use official [Python client library](https://docs.apify.com/api/client/python.md): ```bash pip install apify-client ``` In shell scripts, use [Apify CLI](https://docs.apify.com/cli/docs.md): ````bash # MacOS / Linux curl -fsSL https://apify.com/install-cli.sh | bash # Windows irm https://apify.com/install-cli.ps1 | iex ```bash In AI frameworks, you might use the [Apify MCP server](https://docs.apify.com/platform/integrations/mcp.md). If your project is in a different language, use the [REST API](https://docs.apify.com/api/v2.md). For usage examples, see the [API](#api) section below. For more details, see Apify documentation as [Markdown index](https://docs.apify.com/llms.txt) and [Markdown full-text](https://docs.apify.com/llms-full.txt). # README ![ParseForge Banner](https://github.com/ParseForge/apify-assets/blob/ad35ccc13ddd068b9d6cba33f323962e39aed5b2/banner.jpg?raw=true) ## ๐ŸŽค Audio Transcriber > ๐Ÿš€ **Convert speech to text in seconds.** Upload audio files and get accurate transcriptions. Supports multiple languages. No coding, no transcription accounts required. > ๐Ÿ•’ **Last updated:** 2026-05-08 ยท **๐ŸŒ Multi-language** ยท **๐ŸŽง Any audio format** ยท **๐Ÿ“ Full transcription** ยท **๐Ÿšซ No auth** required
Pull structured records from Audio Transcriber โ€” clean fields ready as CSV, JSON, JSONL, Excel, or XML for downstream pipelines.
##### Copy to your AI assistant Copy this block into ChatGPT, Claude, Cursor, or any LLM to start using this actor. ```` parseforge/audio-transcriber on Apify. Call: ApifyClient("TOKEN").actor("parseforge/audio-transcriber").call(run\_input={...}), then client.dataset(run\["defaultDatasetId"]).list\_items().items for results. Key inputs: audioFileUrl (array, default \["https://upload.wikimedia.org/wikipedia/commons/e/e9/Mia\_Lo), language (string, default "en"). Full actor spec: fetch build via GET https://api.apify.com/v2/acts/parseforge~audio-transcriber (Bearer TOKEN). Get token: https://console.apify.com/account/integrations ```` Convert audio recordings to clean, structured text without juggling transcription tools or paying per-minute fees. The Actor accepts one or more audio file URLs (MP3, WAV, AIFF, AAC, OGG, FLAC, M4A and similar), runs each through an AI transcription pipeline, and returns the full transcript in your dataset. Built for podcasters, journalists, researchers, meeting teams, and any workflow that turns spoken audio into searchable text. The output is a structured record per file: a back-reference to the input URL, the full transcription, a timestamp, and an error field if something fails. Hand the dataset off to your editor, summarizer, or downstream pipeline. Every run is processed live, so there is no upload cap or vendor lock-in. | ๐Ÿ‘ฅ Built for | ๐ŸŽฏ Primary use cases | |---|---| | Podcasters and creators | Generate episode transcripts and show notes | | Journalists and researchers | Convert recorded interviews into searchable text | | Meeting and operations teams | Auto-transcribe Zoom and Teams recordings | | Content marketing | Repurpose webinars into blog posts and shorts | | Accessibility teams | Produce captions and transcripts for compliance | | Localization workflows | Get base text ready for translation pipelines | --- ### ๐Ÿ“‹ What the Audio Transcriber does - ๐ŸŽง **Audio input.** Accepts one or more audio file URLs in common formats (MP3, WAV, AIFF, AAC, OGG, FLAC, M4A). - ๐ŸŒ **Language hint.** Pass an ISO 639-1 language code (e.g. en, es, fr, pt) to bias the model toward the right phonetics and vocabulary. - ๐Ÿ“ **Full transcription.** Returns the complete text of each audio file as a single string per record. - ๐Ÿ†” **Back-reference.** Every record includes the original audio URL so you can rejoin transcripts to source files. - โฑ๏ธ **Timestamp.** Every record carries a timestamp field with the time the transcript was produced. - โ— **Per-file error reporting.** If a file fails (corrupt, unsupported, unreadable URL) the error appears on its own record without breaking the run. The actor processes uploads in the order you provide them. Records stream into the dataset as transcripts complete, so you can start consuming results before the run is fully finished. Manual transcription typically takes 4-6 hours per hour of audio; this Actor returns the same text in minutes. > ๐Ÿ’ก **Why it matters:** spoken audio is everywhere (podcasts, interviews, meetings) but most data tooling is text-first. A reliable speech-to-text step unlocks search, summarization, translation, and analytics workflows that would otherwise be impossible. --- ### ๐ŸŽฌ Full Demo ๐Ÿšง Coming soon: a 3-minute walkthrough showing audio upload, a live run, and how to feed the transcript into a summarization workflow. --- ### โš™๏ธ Input | Field | Type | Name | Description | |---|---|---|---| | audioFileUrl | array of strings | Audio File URL | Required. One or more audio file URLs (MP3, WAV, AIFF, AAC, OGG, FLAC, M4A). Files are processed in the order you provide them. | | language | string | Language | ISO 639-1 language code (e.g. en, es, fr, pt) to guide the model. Leave empty for auto-detect. | Example 1. English podcast episode transcription. ```json { "audioFileUrl": [ "https://example.com/podcast/episode-12.mp3" ], "language": "en" } ```` Example 2. Batch processing of 3 Spanish-language interviews. ```json { "audioFileUrl": [ "https://example.com/interview-1.wav", "https://example.com/interview-2.wav", "https://example.com/interview-3.wav" ], "language": "es" } ``` > โš ๏ธ **Good to Know:** the audio URL must be publicly reachable. If your file lives in a private bucket, generate a signed URL valid for the run's duration before passing it in. *** ### ๐Ÿ“Š Output The dataset returns one record per audio file. Each record carries the original URL, the full transcription text, a timestamp, and an optional error message if processing failed. Consume the dataset as JSON, CSV, Excel, XML, or RSS via the Apify console or API. #### ๐Ÿงพ Schema | Field | Type | Example | |---|---|---| | ๐Ÿ”— audioReference | string (url) | `https://example.com/podcast/episode-12.mp3` | | ๐Ÿ“ transcription | string | `Welcome back to the show, today we're talking about...` | | ๐Ÿ“… timestamp | ISO datetime | `2026-05-08T12:00:00.000Z` | | โ— error | string or null | null | #### ๐Ÿ“ฆ Sample records ##### 1. Typical record (English podcast) ```json { "audioReference": "https://example.com/podcast/episode-12.mp3", "transcription": "Welcome back to the show, today we're talking about how small teams can ship faster without burning out. Our guest today has been building products at venture-backed startups for over a decade and has a lot to share.", "timestamp": "2026-05-08T12:00:00.000Z", "error": null } ``` ##### 2. Spanish interview (multilingual hint) ```json { "audioReference": "https://example.com/interview-2.wav", "transcription": "Buenos dias, gracias por tomarse el tiempo de hablar conmigo. Mi primera pregunta tiene que ver con como empezo el proyecto y que les motivo a escoger esa direccion en particular.", "timestamp": "2026-05-08T12:00:00.000Z", "error": null } ``` ##### 3. Error record (file unreadable) ```json { "audioReference": "https://example.com/broken-link.mp3", "transcription": null, "timestamp": "2026-05-08T12:00:00.000Z", "error": "Could not download audio: HTTP 404" } ``` *** ### โœจ Why choose this Actor | | Capability | |---|---| | ๐ŸŽฏ | **Built for the job.** Audio-to-text only, no extra knobs to learn or configure. | | ๐ŸŒ | **Multi-language.** Pass an ISO code for biased decoding or leave empty for auto-detect. | | โšก | **Fast.** Most files transcribe in 1-3 minutes per minute of audio. | | ๐Ÿ” | **Live processing.** Every run runs end to end with no caching of input audio. | | ๐ŸŒ | **No infra to manage.** Apify handles compute, scaling, scheduling, and storage. | | ๐Ÿ›ก๏ธ | **Reliable.** Per-file error reporting means one bad URL does not kill the whole run. | | ๐Ÿšซ | **No code required.** Configure in the UI, run from CLI, schedule via cron, or call from any language with the Apify SDK. | > ๐Ÿ“Š Production-grade speech-to-text without the engineering overhead of building and maintaining your own pipeline. *** ### ๐Ÿ“ˆ How it compares to alternatives | Approach | Cost | Coverage | Refresh | Accuracy | Setup | |---|---|---|---|---|---| | **โญ Audio Transcriber** *(this Actor)* | $5 free credit, then pay-per-use | Any audio URL | **Live per run** | High | โšก 2 min | | Manual transcription | Hours of human time | High control | Per file | Highest | ๐Ÿข Hours per file | | Paid transcription SaaS | $$$ monthly | High | Live | High | โณ Hours of integration | | Self-hosted models | Engineering hours | High once built | Live | Variable | ๐Ÿข Days to weeks | Pick this Actor when you want fast, reliable transcription without owning the infrastructure or paying per-minute SaaS fees. *** ### ๐Ÿš€ How to use 1. ๐Ÿ“ **Sign up.** [Create a free account with $5 credit](https://console.apify.com/sign-up?fpr=vmoqkp) (takes 2 minutes). 2. ๐ŸŒ **Open the Actor.** Go to the Audio Transcriber page on the Apify Store. 3. ๐ŸŽฏ **Add your audio.** Paste one or more audio URLs into audioFileUrl and (optionally) set language. 4. ๐Ÿš€ **Run it.** Click **Start** and let the Actor transcribe each file. 5. ๐Ÿ“ฅ **Download.** Grab your results in the **Dataset** tab as CSV, Excel, JSON, or XML. > โฑ๏ธ Total time from signup to first transcript: **3-5 minutes** for a short clip. *** ### ๐Ÿ’ผ Business use cases
#### ๐Ÿ“Š Content and editorial - Generate searchable transcripts for podcasts and webinars - Repurpose audio into blog posts, social clips, and newsletters - Build show notes and chapter markers from spoken word - Index your back-catalog for full-text search #### ๐Ÿข Operations and meetings - Auto-transcribe internal recordings and standups - Build searchable archives of customer calls - Pull action items from leadership all-hands - Capture compliance evidence from recorded sessions
#### ๐ŸŽฏ Research and journalism - Turn interview recordings into editable text - Speed up qualitative research and coding - Build court-of-public-opinion archives from speeches - Localize source audio for translation pipelines #### ๐Ÿ› ๏ธ Engineering and product - Add speech-to-text to your product without owning a model - Wire transcripts into AI summarization workflows - Build accessibility features and captions - Prototype voice-driven features quickly
*** ### ๐ŸŒŸ Beyond business use cases Data like this powers more than commercial workflows. The same structured records support research, education, civic projects, and personal initiatives.
#### ๐ŸŽ“ Research and academia - Empirical datasets for papers, thesis work, and coursework - Longitudinal studies tracking changes across snapshots - Reproducible research with cited, versioned data pulls - Classroom exercises on data analysis and ethical scraping #### ๐ŸŽจ Personal and creative - Side projects, portfolio demos, and indie app launches - Data visualizations, dashboards, and infographics - Content research for bloggers, YouTubers, and podcasters - Hobbyist collections and personal trackers
#### ๐Ÿค Non-profit and civic - Transparency reporting and accountability projects - Advocacy campaigns backed by public-interest data - Community-run databases for local issues - Investigative journalism on public records #### ๐Ÿงช Experimentation - Prototype AI and machine-learning pipelines with real data - Validate product-market hypotheses before engineering spend - Train small domain-specific models on niche corpora - Test dashboard concepts with live input
*** ### ๐Ÿ”Œ Automating Audio Transcriber This Actor exposes a REST endpoint, so you can drive it from any language or workflow tool. - **Node.js** - call it via the [Apify JS SDK](https://docs.apify.com/sdk/js). - **Python** - call it via the [Apify Python SDK](https://docs.apify.com/sdk/python). - **REST** - hit it directly through the [Apify v2 API](https://docs.apify.com/api/v2). **Schedules.** Use Apify Scheduler to transcribe a folder of audio URLs on a cron cadence. Combine with webhooks to trigger downstream summarization or translation workflows the moment a transcript is ready. *** ### โ“ Frequently Asked Questions
๐Ÿ’ณ Do I need a paid Apify plan to run this actor? No. You can start right now on the free Apify plan, which includes **$5 in monthly credit**. That is enough to run the actor several times and explore the output. Paid plans unlock higher item caps, more concurrent runs, and larger datasets. [Create a free Apify account here](https://console.apify.com/sign-up?fpr=vmoqkp).
๐Ÿšจ What happens if my run fails or returns no results? Failed runs are not charged. If a single audio URL fails, the actor records the error on that record only and continues with the rest of the batch. If the whole run fails, re-run it or open our [contact form](https://tally.so/r/BzdKgA) and we will look into it.
๐Ÿ“ How long can my audio files be? There is no hard cap. Longer files take proportionally longer to process. We recommend splitting recordings longer than 60 minutes into smaller chunks for faster results and easier downstream editing.
๐ŸŽผ What audio formats are supported? MP3, WAV, AIFF, AAC, OGG, FLAC, and M4A are all supported. Pass any public URL pointing to one of these formats. Streams (HLS, DASH) are not supported.
๐ŸŒ Which languages does it handle? Most major languages are supported. Pass an ISO 639-1 code like en, es, fr, de, pt, it, ja, zh to bias the model. Leave the field empty for auto-detect.
๐Ÿง‘โ€๐Ÿ’ป Can I call this actor from my own code? Yes. Apify exposes every actor as a REST endpoint and ships first-class SDKs for [Node.js](https://docs.apify.com/sdk/js) and [Python](https://docs.apify.com/sdk/python). You can start a run, read the dataset, and handle webhooks from your own app in a few lines.
๐Ÿ“ค How do I export the data? Every Apify dataset can be downloaded in one click as CSV, JSON, JSONL, Excel, HTML, XML, or RSS. You can also pull results programmatically via the [Apify API](https://docs.apify.com/api/v2) or stream into BigQuery, S3, and other destinations through built-in integrations.
๐Ÿ“… Can I schedule the actor to run automatically? Yes. Use the Apify scheduler to run the actor on any cadence, from hourly to monthly. Drop new audio URLs into the input each cycle, or wire the actor to fire on a webhook from your CMS or recording platform.
๐Ÿช Can I use the data commercially? Yes. Transcripts of audio you have rights to are yours to use in your own internal pipelines, products, and reports.
๐Ÿ’ผ Which plan should I pick for production use? Apify's Starter and Scale plans are designed for production workloads. They give you faster instances, more concurrent runs, and higher quotas. Pick the plan that matches your audio volume and refresh cadence; the in-app pricing calculator will help you size it.
๐Ÿ› ๏ธ Can you add timestamps or speaker labels? Open the [contact form](https://tally.so/r/BzdKgA) and tell us about your use case. We add features regularly when there is a clear use case behind the request.
โš–๏ธ Is it legal to transcribe audio with this Actor? Yes, provided you have rights to the audio. You are responsible for compliance with copyright, privacy, and consent laws in your jurisdiction. ***
### ๐Ÿ”Œ Integrate with any app Audio Transcriber connects to any cloud service via [Apify integrations](https://apify.com/integrations): - [**Make**](https://docs.apify.com/platform/integrations/make) - Automate multi-step workflows - [**Zapier**](https://docs.apify.com/platform/integrations/zapier) - Connect with 5,000+ apps - [**Slack**](https://docs.apify.com/platform/integrations/slack) - Get run notifications in your channels - [**Airbyte**](https://docs.apify.com/platform/integrations/airbyte) - Pipe results into your warehouse - [**GitHub**](https://docs.apify.com/platform/integrations/github) - Trigger runs from commits and releases - [**Google Drive**](https://docs.apify.com/platform/integrations/drive) - Export datasets straight to Sheets You can also use webhooks to trigger downstream actions when a transcript completes, like firing a summarization actor or pinging a Slack channel. *** ### ๐Ÿ”— Recommended Actors - [**๐ŸŽฌ YouTube AI Transcriber**](https://apify.com/parseforge/youtube-ai-transcriber) - Transcribe YouTube videos via URL with full metadata - [**๐Ÿ–ผ๏ธ Auto Video Thumbnail Generator**](https://apify.com/parseforge/auto-video-thumbnail-generator) - Auto-generate thumbnails from video uploads - [**๐Ÿ“ฐ Article Extractor**](https://apify.com/parseforge/article-extractor) - Extract clean article text from any URL - [**๐Ÿ“„ PDF to JSON Parser**](https://apify.com/parseforge/pdf-to-json-parser) - Convert PDFs into structured JSON - [**๐Ÿ” RAG Web Browser**](https://apify.com/parseforge/rag-web-browser) - Fetch clean text for AI retrieval pipelines > ๐Ÿ’ก **Pro Tip:** browse the complete [ParseForge collection](https://apify.com/parseforge) for more reference-data scrapers. *** **๐Ÿ†˜ Need Help?** [**Open our contact form**](https://tally.so/r/BzdKgA) to request a new actor, propose a custom project, or report an issue. *** > โš ๏ธ **Disclaimer.** This Actor is an independent tool. The scraper accesses only audio you supply by URL and is intended for legitimate research, productivity, and content workflows. Users are responsible for ensuring they hold the rights to transcribe the audio they submit and for compliance with copyright, privacy, and consent laws in their jurisdiction. # Actor input Schema ## `audioFileUrl` (type: `array`): Upload one or more audio files (MP3, WAV, AIFF, AAC, OGG, FLAC). Files are processed in the order you provide them. ## `language` (type: `string`): ISO 639-1 language code (e.g., 'en', 'es', 'fr', 'pt') to guide the transcription model toward the right pronunciation and terms. ## Actor input object example ```json { "audioFileUrl": [ "https://upload.wikimedia.org/wikipedia/commons/e/e9/Mia_Love_speaks_in_opposition_to_the_Joint_Comprehensive_Plan_of_Action.ogg" ], "language": "en" } ``` # Actor output Schema ## `transcriptions` (type: `string`): Complete dataset with all transcriptions including audio reference, transcription text, and timestamp ## `overview` (type: `string`): Overview view of transcriptions with key fields displayed in a table format # API You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup. ## JavaScript example ```javascript import { ApifyClient } from 'apify-client'; // Initialize the ApifyClient with your Apify API token // Replace the '' with your token const client = new ApifyClient({ token: '', }); // Prepare Actor input const input = { "audioFileUrl": [ "https://upload.wikimedia.org/wikipedia/commons/e/e9/Mia_Love_speaks_in_opposition_to_the_Joint_Comprehensive_Plan_of_Action.ogg" ], "language": "en" }; // Run the Actor and wait for it to finish const run = await client.actor("parseforge/audio-transcriber").call(input); // Fetch and print Actor results from the run's dataset (if any) console.log('Results from dataset'); console.log(`๐Ÿ’พ Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`); const { items } = await client.dataset(run.defaultDatasetId).listItems(); items.forEach((item) => { console.dir(item); }); // ๐Ÿ“š Want to learn more ๐Ÿ“–? Go to โ†’ https://docs.apify.com/api/client/js/docs ``` ## Python example ```python from apify_client import ApifyClient # Initialize the ApifyClient with your Apify API token # Replace '' with your token. client = ApifyClient("") # Prepare the Actor input run_input = { "audioFileUrl": ["https://upload.wikimedia.org/wikipedia/commons/e/e9/Mia_Love_speaks_in_opposition_to_the_Joint_Comprehensive_Plan_of_Action.ogg"], "language": "en", } # Run the Actor and wait for it to finish run = client.actor("parseforge/audio-transcriber").call(run_input=run_input) # Fetch and print Actor results from the run's dataset (if there are any) print("๐Ÿ’พ Check your data here: https://console.apify.com/storage/datasets/" + run["defaultDatasetId"]) for item in client.dataset(run["defaultDatasetId"]).iterate_items(): print(item) # ๐Ÿ“š Want to learn more ๐Ÿ“–? Go to โ†’ https://docs.apify.com/api/client/python/docs/quick-start ``` ## CLI example ```bash echo '{ "audioFileUrl": [ "https://upload.wikimedia.org/wikipedia/commons/e/e9/Mia_Love_speaks_in_opposition_to_the_Joint_Comprehensive_Plan_of_Action.ogg" ], "language": "en" }' | apify call parseforge/audio-transcriber --silent --output-dataset ``` ## MCP server setup ```json { "mcpServers": { "apify": { "command": "npx", "args": [ "mcp-remote", "https://mcp.apify.com/?tools=parseforge/audio-transcriber", "--header", "Authorization: Bearer " ] } } } ``` ## OpenAPI specification ```json { "openapi": "3.0.1", "info": { "title": "Audio Transcriber", "description": "Automates audio transcription from multiple sources (files or links). Normalizes input format to ensure optimal processing. Generates word-for-word transcriptions maintaining references to source audio, perfect for datasets requiring traceability and regulatory compliance.", "version": "1.0", "x-build-id": "sZrmoyN8YcMZAJkby" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/parseforge~audio-transcriber/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-parseforge-audio-transcriber", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/parseforge~audio-transcriber/runs": { "post": { "operationId": "runs-sync-parseforge-audio-transcriber", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/parseforge~audio-transcriber/run-sync": { "post": { "operationId": "run-sync-parseforge-audio-transcriber", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } } }, "components": { "schemas": { "inputSchema": { "type": "object", "required": [ "audioFileUrl" ], "properties": { "audioFileUrl": { "title": "Audio File URL", "type": "array", "description": "Upload one or more audio files (MP3, WAV, AIFF, AAC, OGG, FLAC). Files are processed in the order you provide them.", "items": { "type": "string" } }, "language": { "title": "Language", "type": "string", "description": "ISO 639-1 language code (e.g., 'en', 'es', 'fr', 'pt') to guide the transcription model toward the right pronunciation and terms." } } }, "runsResponseSchema": { "type": "object", "properties": { "data": { "type": "object", "properties": { "id": { "type": "string" }, "actId": { "type": "string" }, "userId": { "type": "string" }, "startedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "finishedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "status": { "type": "string", "example": "READY" }, "meta": { "type": "object", "properties": { "origin": { "type": "string", "example": "API" }, "userAgent": { "type": "string" } } }, "stats": { "type": "object", "properties": { "inputBodyLen": { "type": "integer", "example": 2000 }, "rebootCount": { "type": "integer", "example": 0 }, "restartCount": { "type": "integer", "example": 0 }, "resurrectCount": { "type": "integer", "example": 0 }, "computeUnits": { "type": "integer", "example": 0 } } }, "options": { "type": "object", "properties": { "build": { "type": "string", "example": "latest" }, "timeoutSecs": { "type": "integer", "example": 300 }, "memoryMbytes": { "type": "integer", "example": 1024 }, "diskMbytes": { "type": "integer", "example": 2048 } } }, "buildId": { "type": "string" }, "defaultKeyValueStoreId": { "type": "string" }, "defaultDatasetId": { "type": "string" }, "defaultRequestQueueId": { "type": "string" }, "buildNumber": { "type": "string", "example": "1.0.0" }, "containerUrl": { "type": "string" }, "usage": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "integer", "example": 1 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } }, "usageTotalUsd": { "type": "number", "example": 0.00005 }, "usageUsd": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "number", "example": 0.00005 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } } } } } } } } } ```