Podcast Transcriber & Analyzer
Pricing
from $12.00 / 1,000 speech to text transcriptions
Go to Apify Store
Podcast Transcriber & Analyzer
Download, Transcribe and analyze any podcast from an RSS feed, Apple Podcasts link, show name, or episode URL.
Podcast Transcriber & Analyzer
Pricing
from $12.00 / 1,000 speech to text transcriptions
Download, Transcribe and analyze any podcast from an RSS feed, Apple Podcasts link, show name, or episode URL.
You can access the Podcast Transcriber & Analyzer programmatically from your own applications by using the Apify API. You can also choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in Integrations settings in Apify Console.
{ "openapi": "3.0.1", "info": { "version": "0.0", "x-build-id": "s57L0Kx4JxdwNI4Fv" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/hgservices~podcast-transcriber/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-hgservices-podcast-transcriber", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/hgservices~podcast-transcriber/runs": { "post": { "operationId": "runs-sync-hgservices-podcast-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/hgservices~podcast-transcriber/run-sync": { "post": { "operationId": "run-sync-hgservices-podcast-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": [ "source" ], "properties": { "source": { "title": "Podcast source (RSS feed, Apple link, show name, or episode URL)", "type": "string", "description": "Provide exactly one podcast reference — the type is auto-detected:\n- **RSS/Atom feed** — e.g. https://feeds.buzzsprout.com/1195244.rss\n- **Apple Podcasts link** — any podcasts.apple.com URL; add `?i=<episodeId>` to pin a single episode\n- **Show name** — resolved to its feed via the iTunes Search API\n- **Direct episode/audio URL** — an .mp3/.m4a/etc. file (or an episode web page); transcribed as a single episode" }, "episodeSelection": { "title": "Which episodes", "enum": [ "latest", "all", "dateRange", "index", "guid", "titleMatch" ], "type": "string", "description": "How to pick episodes from a feed/show. 'latest' = newest episode only.", "default": "latest" }, "maxEpisodes": { "title": "Max episodes", "minimum": 1, "type": "integer", "description": "Optional convenience cap for 'all'/'dateRange'. Leave empty for no cap — your run is bounded by your Apify credits and the run timeout." }, "fromDate": { "title": "From date (ISO)", "type": "string", "description": "For 'dateRange': only episodes published on/after this ISO date." }, "toDate": { "title": "To date (ISO)", "type": "string", "description": "For 'dateRange': only episodes published on/before this ISO date." }, "episodeIndex": { "title": "Episode index", "minimum": 0, "type": "integer", "description": "For 'index': 0 = newest, 1 = next, ...", "default": 0 }, "episodeGuid": { "title": "Episode GUID", "type": "string", "description": "For 'guid': the exact episode GUID to select." }, "titleContains": { "title": "Title contains", "type": "string", "description": "For 'titleMatch': select episodes whose title contains this text (case-insensitive)." }, "includeTranscript": { "title": "Transcribe", "type": "boolean", "description": "Produce a transcript for each episode (transcribed in-process with Deepgram).", "default": true }, "includeAnalysis": { "title": "Analyze (beta)", "type": "boolean", "description": "Run AI analysis on each transcript — summaries, topics, entities, guests, and more. Keyword 'mentions' run independently and don't require this.", "default": true }, "analysis": { "title": "Analyses to run", "type": "array", "description": "Which AI analyses to produce per episode.", "items": { "type": "string", "enum": [ "summary", "chapters", "topics", "entities", "guests", "sentiment", "adReads" ], "enumTitles": [ "Summary", "Chapters", "Topics", "Entities", "Guests", "Sentiment", "Ad reads" ] }, "default": [ "summary", "chapters", "topics", "entities", "guests", "sentiment", "adReads" ] }, "mentions": { "title": "Mention keywords", "type": "array", "description": "Keywords/brands to find in each transcript (deterministic; no API key needed). Powers podcast monitoring.", "default": [], "items": { "type": "string" } }, "includeAudio": { "title": "Store audio file", "type": "boolean", "description": "Download each episode's audio and store it in the key-value store (key 'audio-<guid>').", "default": false }, "subtitleFormats": { "title": "Subtitle export", "type": "array", "description": "Generate subtitle files from the transcript timings and store them in the key-value store (key 'subtitles-<guid>.<ext>'). Their keys appear on each record as 'subtitleKvsKeys'. Requires transcription.", "items": { "type": "string", "enum": [ "srt", "vtt" ], "enumTitles": [ "SRT (.srt)", "WebVTT (.vtt)" ] }, "default": [] }, "diarize": { "title": "Identify speakers", "type": "boolean", "description": "Label different speakers in the transcript.", "default": true }, "smartFormat": { "title": "Smart formatting", "type": "boolean", "description": "Apply punctuation/formatting to the transcript.", "default": true }, "timestamps": { "title": "Timestamps", "type": "boolean", "description": "Prefix each speaker turn in the transcript with its start time (HH:MM:SS), e.g. `[Speaker 1 00:01:58]`.", "default": true }, "maxAudioMinutes": { "title": "Max audio minutes per episode", "minimum": 1, "type": "integer", "description": "Skip (don't transcribe) episodes longer than this. Podcasts are long-form (some interview shows run 4–5 hours), so the default is generous.", "default": 600 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Proxy used when downloading episode audio for transcription.", "default": { "useApifyProxy": true } } } }, "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 } } } } } } } } }}OpenAPI is a standard for designing and describing RESTful APIs, allowing developers to define API structure, endpoints, and data formats in a machine-readable way. It simplifies API development, integration, and documentation.
OpenAPI is effective when used with AI agents and GPTs by standardizing how these systems interact with various APIs, for reliable integrations and efficient communication.
By defining machine-readable API specifications, OpenAPI allows AI models like GPTs to understand and use varied data sources, improving accuracy. This accelerates development, reduces errors, and provides context-aware responses, making OpenAPI a core component for AI applications.
You can download the OpenAPI definitions for Podcast Transcriber & Analyzer from the options below:
If you’d like to learn more about how OpenAPI powers GPTs, read our blog post.
You can also check out our other API clients: