transcript
curl --request GET \
--url https://api.aisa.one/apis/v1/instagram/media/transcript \
--header 'Authorization: Bearer <token>'import requests
url = "https://api.aisa.one/apis/v1/instagram/media/transcript"
headers = {"Authorization": "Bearer <token>"}
response = requests.get(url, headers=headers)
print(response.text)const options = {method: 'GET', headers: {Authorization: 'Bearer <token>'}};
fetch('https://api.aisa.one/apis/v1/instagram/media/transcript', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));<?php
$curl = curl_init();
curl_setopt_array($curl, [
CURLOPT_URL => "https://api.aisa.one/apis/v1/instagram/media/transcript",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "GET",
CURLOPT_HTTPHEADER => [
"Authorization: Bearer <token>"
],
]);
$response = curl_exec($curl);
$err = curl_error($curl);
curl_close($curl);
if ($err) {
echo "cURL Error #:" . $err;
} else {
echo $response;
}package main
import (
"fmt"
"net/http"
"io"
)
func main() {
url := "https://api.aisa.one/apis/v1/instagram/media/transcript"
req, _ := http.NewRequest("GET", url, nil)
req.Header.Add("Authorization", "Bearer <token>")
res, _ := http.DefaultClient.Do(req)
defer res.Body.Close()
body, _ := io.ReadAll(res.Body)
fmt.Println(string(body))
}HttpResponse<String> response = Unirest.get("https://api.aisa.one/apis/v1/instagram/media/transcript")
.header("Authorization", "Bearer <token>")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.aisa.one/apis/v1/instagram/media/transcript")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Get.new(url)
request["Authorization"] = 'Bearer <token>'
response = http.request(request)
puts response.read_body{
"success": true,
"transcripts": [
{
"id": "3597267389859272809",
"shortcode": "DHsD6HGqJhp",
"text": "Let's fry up the perfect bunzel. Beautiful. Everybody, shh. The perfect bunzel. Let me show you my bunzel. When it comes down to bunzel, we make it the crispiest, get the crunch. Heaven."
}
]
}Instagram
transcript
Speech-to-text for a video or reel under two minutes.
GET
https://api.aisa.one
/
apis
/
v1
/
instagram
/
media
/
transcript
transcript
curl --request GET \
--url https://api.aisa.one/apis/v1/instagram/media/transcript \
--header 'Authorization: Bearer <token>'import requests
url = "https://api.aisa.one/apis/v1/instagram/media/transcript"
headers = {"Authorization": "Bearer <token>"}
response = requests.get(url, headers=headers)
print(response.text)const options = {method: 'GET', headers: {Authorization: 'Bearer <token>'}};
fetch('https://api.aisa.one/apis/v1/instagram/media/transcript', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));<?php
$curl = curl_init();
curl_setopt_array($curl, [
CURLOPT_URL => "https://api.aisa.one/apis/v1/instagram/media/transcript",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "GET",
CURLOPT_HTTPHEADER => [
"Authorization: Bearer <token>"
],
]);
$response = curl_exec($curl);
$err = curl_error($curl);
curl_close($curl);
if ($err) {
echo "cURL Error #:" . $err;
} else {
echo $response;
}package main
import (
"fmt"
"net/http"
"io"
)
func main() {
url := "https://api.aisa.one/apis/v1/instagram/media/transcript"
req, _ := http.NewRequest("GET", url, nil)
req.Header.Add("Authorization", "Bearer <token>")
res, _ := http.DefaultClient.Do(req)
defer res.Body.Close()
body, _ := io.ReadAll(res.Body)
fmt.Println(string(body))
}HttpResponse<String> response = Unirest.get("https://api.aisa.one/apis/v1/instagram/media/transcript")
.header("Authorization", "Bearer <token>")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.aisa.one/apis/v1/instagram/media/transcript")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Get.new(url)
request["Authorization"] = 'Bearer <token>'
response = http.request(request)
puts response.read_body{
"success": true,
"transcripts": [
{
"id": "3597267389859272809",
"shortcode": "DHsD6HGqJhp",
"text": "Let's fry up the perfect bunzel. Beautiful. Everybody, shh. The perfect bunzel. Let me show you my bunzel. When it comes down to bunzel, we make it the crispiest, get the crunch. Heaven."
}
]
}Returns
Set this endpoint up in your agent →
transcripts, each with id, shortcode and the transcribed text.
The target must be a video under two minutes. A photo post returns 400 bad_request, so when the type of a URL is unknown, check is_video with get_instagram_post first.
Measured at 13 seconds, the slowest call in this API, for about 1 KB back. For the caption the author wrote rather than the words spoken, read edge_media_to_caption from get_instagram_post.
Example
curl "https://api.aisa.one/apis/v1/instagram/media/transcript?url=VALUE" \
-H "Authorization: Bearer YOUR_API_KEY"
// Copy this whole block into Claude Code, Codex, Cursor or any coding agent.
// It carries everything needed to connect, authorize and run this example —
// no key to paste, one click of Allow in the browser.
{
"calls": [
{
"call_id": "1",
"tool": "get_instagram_media_transcript",
"arguments": {
"url": "VALUE"
}
}
]
}
// ── for the agent ─────────────────────────────────────────────────────────
// Register the AIsa MCP server, then call its `batch_quote` tool with the JSON above.
// name aisa
// endpoint https://mcp.aisa.one/mcp
// transport streamable-http
// auth OAuth. The server publishes RFC 9728 metadata, so open a
// browser and the user clicks Allow once — nothing to paste.
// If AISA_API_KEY is set, send it as a bearer header instead.
// Use your own MCP mechanism, not a hand-edited config file:
// Codex codex mcp add aisa --url https://mcp.aisa.one/mcp
// Claude Code claude mcp add --transport http -s user aisa https://mcp.aisa.one/mcp
// Cursor / VS Code a "url" entry for https://mcp.aisa.one/mcp in the MCP config
// The server reaches https://mcp.aisa.one/servers worth of APIs through a few meta
// tools: search, list_categories, get_details, batch_quote, batch_use.
// search, get_details and batch_quote are free; batch_use is billed per
// call. This operation's full contract — every argument, the response
// shape, the price and the pitfalls — is at
// https://aisa.one/docs/api-reference/instagram/get_instagram-media-transcript.md
// Show me the quoted cost. Once I approve, run the same calls with
// batch_use and show me the result.
First time? Point any MCP client at
https://mcp.aisa.one/mcp — Claude
Code, Codex, Cursor, VS Code and the rest. Authorization is OAuth: the client
opens a browser, you click Allow once, and there is no key to paste. Your
agent then reaches every endpoint through a few meta tools: search,
list_categories, get_details and batch_quote are free, batch_use is
billed per call. Setup per client is in
Connect via MCP; the live tool list and what each call
costs are on aisa.one/mcp.Request contract
- Method and path: GET /apis/v1/instagram/media/transcript
- Availability: enabled
- Request URL template:
https://api.aisa.one/apis/v1/instagram/media/transcript - allow_long_transcription: query; optional
- cache_max_age: query; optional
- url: query; required
- Runtime facts: fdf0a203e7ec628291b62272da7b8bbbe431c8f77f251ea2e65c19cd3c98fa37
{
"operationId": "get_instagram_media_transcript",
"method": "GET",
"path": "/apis/v1/instagram/media/transcript",
"servers": [
{
"url": "https://api.aisa.one"
}
],
"parameters": [
{
"description": "Paid opt-in, enabled only by the literal query value 'true' (allow_long_transcription=true). Defaults to false when omitted; other values do not enable paid mode. By default, successful AI transcription of videos up to 120 seconds (two minutes, inclusive) costs a flat 1 credit per request. Over 120 seconds, videos cannot be AI-transcribed by default. Set allow_long_transcription=true to opt into paid AI with no fixed duration cap: ALL successful AI transcriptions in this mode cost 10 credits per started minute, including short videos: 10 * ceil(duration_seconds / 60). For example, 177 seconds costs 30 credits and an opted-in 60 seconds costs 10 credits. Empty AI results and errors cost 0 credits for AI transcription. This flag does not force AI and does not enable transcription or AI fallback by itself. Keep get_transcript=true or use_ai_as_fallback=true where required by the endpoint. Returned native captions still cost 1 credit on dedicated transcript routes, even for long videos with this flag; on detail routes they leave the base price unchanged. These routes remain synchronous. Allow at least 30 seconds on your client. Paid long transcription can exceed resource limits or timeouts, so successful transcription of long videos is not guaranteed.\n\nProvider reference (supplier schema): `{\"default\":false,\"type\":\"boolean\"}`.",
"in": "query",
"name": "allow_long_transcription",
"required": false,
"schema": {
"type": "boolean"
}
},
{
"description": "If we have a response in the cache that is this many days old or newer, return the cached response (0 credits, with \"cached\": true and a \"cached_at\" timestamp). Otherwise, scrape a live result (By default, successful AI up to 120 seconds costs a flat 1 credit per request; over 120 seconds requires allow_long_transcription=true, which bills ALL successful AI at 10 credits per started minute, including short videos; empty AI results and errors cost 0 credits). [See the Caching page for details.](https://docs.scrapecreators.com/caching)",
"in": "query",
"name": "cache_max_age",
"required": false,
"schema": {
"enum": [
"14d",
"1d",
"30d",
"3d",
"7d"
],
"type": "string"
}
},
{
"description": "Instagram post or reel URL",
"in": "query",
"name": "url",
"required": true,
"schema": {
"type": "string"
}
}
],
"security": [
{
"bearerAuth": []
}
],
"x-aisa-status": "enabled",
"x-aisa-pricing": {
"cost_contract": "response_count",
"customer_multiplier": 1.0,
"customer_pricing": "provider_cost_multiplier",
"default_request_estimate_usd": 0.00188,
"estimate_source": "profile_seed",
"evidence_source": "response_body"
},
"components": {
"securitySchemes": {
"bearerAuth": {
"scheme": "bearer",
"type": "http"
}
}
}
}
Cost and request rules
Usage-based billing; Default request estimate: $0.00188 USD (not a fixed price). Account-specific pricing and final settlement may differ. Published reference values are not an account-specific quote or a settled charge. For endpoints supporting X-AISA-Cost-Mode: quote, obtain a free quote for your exact request before execution; reconcile the settled cost with response metadata and Usage Logs. USD amounts use 1,000,000 integer micro-USD per dollar.- Default request reference estimate (USD): 0.00188
- Cost contract: response_count
- Published reference multiplier: 1.0
- Settlement evidence source: response_body
Authorizations
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Query Parameters
Paid opt-in, enabled only by the literal query value 'true' (allow_long_transcription=true). Defaults to false when omitted; other values do not enable paid mode. By default, successful AI transcription of videos up to 120 seconds (two minutes, inclusive) costs a flat 1 credit per request. Over 120 seconds, videos cannot be AI-transcribed by default. Set allow_long_transcription=true to opt into paid AI with no fixed duration cap: ALL successful AI transcriptions in this mode cost 10 credits per started minute, including short videos: 10 * ceil(duration_seconds / 60). For example, 177 seconds costs 30 credits and an opted-in 60 seconds costs 10 credits. Empty AI results and errors cost 0 credits for AI transcription. This flag does not force AI and does not enable transcription or AI fallback by itself. Keep get_transcript=true or use_ai_as_fallback=true where required by the endpoint. Returned native captions still cost 1 credit on dedicated transcript routes, even for long videos with this flag; on detail routes they leave the base price unchanged. These routes remain synchronous. Allow at least 30 seconds on your client. Paid long transcription can exceed resource limits or timeouts, so successful transcription of long videos is not guaranteed.
Provider reference (supplier schema): {"default":false,"type":"boolean"}.
If we have a response in the cache that is this many days old or newer, return the cached response (0 credits, with "cached": true and a "cached_at" timestamp). Otherwise, scrape a live result (By default, successful AI up to 120 seconds costs a flat 1 credit per request; over 120 seconds requires allow_long_transcription=true, which bills ALL successful AI at 10 credits per started minute, including short videos; empty AI results and errors cost 0 credits). See the Caching page for details.
Available options:
14d, 1d, 30d, 3d, 7d Instagram post or reel URL