AI transcription

#Step 1: Get models & parameters

GET/v1/ai/tools

Call this endpoint to discover every action, its available models, and the JSON schema each model accepts for params. Use the schema from the response to build your params object in step 2.

curl "https://api.rendley.com/v1/ai/tools" \
  -H "Authorization: Bearer YOUR_API_KEY"

const res = await fetch("https://api.rendley.com/v1/ai/tools", {
  headers: { Authorization: "Bearer YOUR_API_KEY" },
});
const { data } = await res.json();

import requests

res = requests.get(
    "https://api.rendley.com/v1/ai/tools",
    headers={"Authorization": "Bearer YOUR_API_KEY"},
)
data = res.json()["data"]

$ch = curl_init("https://api.rendley.com/v1/ai/tools");
curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
curl_setopt($ch, CURLOPT_HTTPHEADER, ["Authorization: Bearer YOUR_API_KEY"]);

$response = curl_exec($ch);
curl_close($ch);
$data = json_decode($response, true)["data"];

package main

import (
	"fmt"
	"io"
	"net/http"
)

func main() {
	req, _ := http.NewRequest("GET", "https://api.rendley.com/v1/ai/tools", nil)
	req.Header.Set("Authorization", "Bearer YOUR_API_KEY")
	res, _ := http.DefaultClient.Do(req)
	defer res.Body.Close()
	b, _ := io.ReadAll(res.Body)
	fmt.Println(string(b))
}

require "net/http"
require "json"

uri = URI("https://api.rendley.com/v1/ai/tools")
req = Net::HTTP::Get.new(uri)
req["Authorization"] = "Bearer YOUR_API_KEY"

res = Net::HTTP.start(uri.hostname, uri.port, use_ssl: true) { |http| http.request(req) }
data = JSON.parse(res.body)["data"]

API key

Response

{
  "data": [
    {
      "action": "generate_video",
      "models": [
        {
          "id": "kling-v2.6",
          "name": "Kling v2.6",
          "schema": {
            "properties": {
              "prompt": { "type": "string" },
              "aspect_ratio": { "type": "string" }
            },
            "required": ["prompt"]
          }
        }
      ]
    }
  ]
}

Step 2 is the specific generation endpoint below. Pick the one you need, pass project_id, optionally model_id, and the params from the schema above.

#Transcribe audio or video

POST/v1/ai/transcribe

Enqueue a job to transcribe spoken words in an audio or video clip to text with word-level timestamps.

Request body

clip_idstringOptional

file_urlstringOptional

model_idstringOptional

Which model to use. Call GET /ai/tools to see available models. Each action has a default.

paramsjsonRequired

Model-specific parameters. Call GET /ai/tools to get the schema for each model.

project_idstringRequired

Response codes

200

400

Bad Request

401

Unauthorized

402

Payment Required

curl -X POST "https://api.rendley.com/v1/ai/transcribe" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "params": {
      "prompt": "..."
    },
    "project_id": "<project_id>"
  }'

const res = await fetch("https://api.rendley.com/v1/ai/transcribe", {
  method: "POST",
  headers: { Authorization: "Bearer YOUR_API_KEY", "Content-Type": "application/json" },
  body: JSON.stringify({
    "params": {
      "prompt": "..."
    },
    "project_id": "<project_id>"
  }),
});
const { data } = await res.json();

import requests

res = requests.post(
    "https://api.rendley.com/v1/ai/transcribe",
    headers={"Authorization": "Bearer YOUR_API_KEY"},
    json={
      "params": {
        "prompt": "..."
      },
      "project_id": "<project_id>"
    },
)
data = res.json()["data"]

$ch = curl_init("https://api.rendley.com/v1/ai/transcribe");
curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
curl_setopt($ch, CURLOPT_CUSTOMREQUEST, "POST");
curl_setopt($ch, CURLOPT_HTTPHEADER, ["Authorization: Bearer YOUR_API_KEY", "Content-Type: application/json"]);
curl_setopt($ch, CURLOPT_POSTFIELDS, json_encode(["params" => ["prompt" => "..."], "project_id" => "<project_id>"]));

$response = curl_exec($ch);
curl_close($ch);
$data = json_decode($response, true)["data"];

package main

import (
	"fmt"
	"io"
	"net/http"
	"bytes"
)

func main() {
	body := bytes.NewBufferString(`{
  "params": {
    "prompt": "..."
  },
  "project_id": "<project_id>"
}`)
	req, _ := http.NewRequest("POST", "https://api.rendley.com/v1/ai/transcribe", body)
	req.Header.Set("Authorization", "Bearer YOUR_API_KEY")
	req.Header.Set("Content-Type", "application/json")
	res, _ := http.DefaultClient.Do(req)
	defer res.Body.Close()
	b, _ := io.ReadAll(res.Body)
	fmt.Println(string(b))
}

require "net/http"
require "json"

uri = URI("https://api.rendley.com/v1/ai/transcribe")
req = Net::HTTP::Post.new(uri)
req["Authorization"] = "Bearer YOUR_API_KEY"
req["Content-Type"] = "application/json"
req.body = { params: { prompt: "..." }, project_id: "<project_id>" }.to_json

res = Net::HTTP.start(uri.hostname, uri.port, use_ssl: true) { |http| http.request(req) }
data = JSON.parse(res.body)["data"]

API key

Body

clip_idstring

file_urlstring

model_idstring

Which model to use. Call GET /ai/tools to see available models. Each action has a default.

paramsREQUIREDjson

Model-specific parameters. Call GET /ai/tools to get the schema for each model.

project_idREQUIREDstring

#Calculate transcription cost

POST/v1/ai/transcribe/cost

Calculate the credit cost of transcribing an audio or video clip.

Request body

clip_idstringOptional

file_urlstringOptional

model_idstringOptional

paramsobjectOptional

project_idstringRequired

Response codes

200

400

Bad Request

401

Unauthorized

curl -X POST "https://api.rendley.com/v1/ai/transcribe/cost" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "project_id": "<project_id>"
  }'

const res = await fetch("https://api.rendley.com/v1/ai/transcribe/cost", {
  method: "POST",
  headers: { Authorization: "Bearer YOUR_API_KEY", "Content-Type": "application/json" },
  body: JSON.stringify({
    "project_id": "<project_id>"
  }),
});
const { data } = await res.json();

import requests

res = requests.post(
    "https://api.rendley.com/v1/ai/transcribe/cost",
    headers={"Authorization": "Bearer YOUR_API_KEY"},
    json={
      "project_id": "<project_id>"
    },
)
data = res.json()["data"]

$ch = curl_init("https://api.rendley.com/v1/ai/transcribe/cost");
curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
curl_setopt($ch, CURLOPT_CUSTOMREQUEST, "POST");
curl_setopt($ch, CURLOPT_HTTPHEADER, ["Authorization: Bearer YOUR_API_KEY", "Content-Type: application/json"]);
curl_setopt($ch, CURLOPT_POSTFIELDS, json_encode(["project_id" => "<project_id>"]));

$response = curl_exec($ch);
curl_close($ch);
$data = json_decode($response, true)["data"];

package main

import (
	"fmt"
	"io"
	"net/http"
	"bytes"
)

func main() {
	body := bytes.NewBufferString(`{
  "project_id": "<project_id>"
}`)
	req, _ := http.NewRequest("POST", "https://api.rendley.com/v1/ai/transcribe/cost", body)
	req.Header.Set("Authorization", "Bearer YOUR_API_KEY")
	req.Header.Set("Content-Type", "application/json")
	res, _ := http.DefaultClient.Do(req)
	defer res.Body.Close()
	b, _ := io.ReadAll(res.Body)
	fmt.Println(string(b))
}

require "net/http"
require "json"

uri = URI("https://api.rendley.com/v1/ai/transcribe/cost")
req = Net::HTTP::Post.new(uri)
req["Authorization"] = "Bearer YOUR_API_KEY"
req["Content-Type"] = "application/json"
req.body = { project_id: "<project_id>" }.to_json

res = Net::HTTP.start(uri.hostname, uri.port, use_ssl: true) { |http| http.request(req) }
data = JSON.parse(res.body)["data"]

API key

Body

clip_idstring

file_urlstring

model_idstring

paramsjson

project_idREQUIREDstring

#Step 3: Poll the job

GET/v1/jobs/{job_id}

Poll this endpoint every few seconds until status is completed or failed. See Jobs and polling for the full loop.

The result contains a media_id and file_hash. Use the next step to get a download URL.

curl "https://api.rendley.com/v1/jobs/{job_id}" \
  -H "Authorization: Bearer YOUR_API_KEY"

const res = await fetch("https://api.rendley.com/v1/jobs/{job_id}", {
  headers: { Authorization: "Bearer YOUR_API_KEY" },
});
const { data } = await res.json();

import requests

res = requests.get(
    "https://api.rendley.com/v1/jobs/{job_id}",
    headers={"Authorization": "Bearer YOUR_API_KEY"},
)
data = res.json()["data"]

$ch = curl_init("https://api.rendley.com/v1/jobs/{job_id}");
curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
curl_setopt($ch, CURLOPT_HTTPHEADER, ["Authorization: Bearer YOUR_API_KEY"]);

$response = curl_exec($ch);
curl_close($ch);
$data = json_decode($response, true)["data"];

package main

import (
	"fmt"
	"io"
	"net/http"
)

func main() {
	req, _ := http.NewRequest("GET", "https://api.rendley.com/v1/jobs/{job_id}", nil)
	req.Header.Set("Authorization", "Bearer YOUR_API_KEY")
	res, _ := http.DefaultClient.Do(req)
	defer res.Body.Close()
	b, _ := io.ReadAll(res.Body)
	fmt.Println(string(b))
}

require "net/http"
require "json"

uri = URI("https://api.rendley.com/v1/jobs/{job_id}")
req = Net::HTTP::Get.new(uri)
req["Authorization"] = "Bearer YOUR_API_KEY"

res = Net::HTTP.start(uri.hostname, uri.port, use_ssl: true) { |http| http.request(req) }
data = JSON.parse(res.body)["data"]

API key

job_idREQUIREDstring

Response

{
  "data": {
    "status": "completed",
    "result_data": "{\"media_id\":\"med_abc...\",\"file_hash\":\"sha256_def...\"}"
  }
}

#Step 4: Get the download URL

GET/v1/uploads

Pass the file_hash from the completed job to get a presigned download URL. The storage_url is time-limited, so download the file promptly.

curl "https://api.rendley.com/v1/uploads" \
  -H "Authorization: Bearer YOUR_API_KEY"

const res = await fetch("https://api.rendley.com/v1/uploads", {
  headers: { Authorization: "Bearer YOUR_API_KEY" },
});
const { data } = await res.json();

import requests

res = requests.get(
    "https://api.rendley.com/v1/uploads",
    headers={"Authorization": "Bearer YOUR_API_KEY"},
)
data = res.json()["data"]

$ch = curl_init("https://api.rendley.com/v1/uploads");
curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
curl_setopt($ch, CURLOPT_HTTPHEADER, ["Authorization: Bearer YOUR_API_KEY"]);

$response = curl_exec($ch);
curl_close($ch);
$data = json_decode($response, true)["data"];

package main

import (
	"fmt"
	"io"
	"net/http"
)

func main() {
	req, _ := http.NewRequest("GET", "https://api.rendley.com/v1/uploads", nil)
	req.Header.Set("Authorization", "Bearer YOUR_API_KEY")
	res, _ := http.DefaultClient.Do(req)
	defer res.Body.Close()
	b, _ := io.ReadAll(res.Body)
	fmt.Println(string(b))
}

require "net/http"
require "json"

uri = URI("https://api.rendley.com/v1/uploads")
req = Net::HTTP::Get.new(uri)
req["Authorization"] = "Bearer YOUR_API_KEY"

res = Net::HTTP.start(uri.hostname, uri.port, use_ssl: true) { |http| http.request(req) }
data = JSON.parse(res.body)["data"]

API key

project_idREQUIREDstring

hashREQUIREDstring

Response

{
  "data": {
    "storage_url": "https://storage.rendley.com/uploads/...png",
    "media_id": "med_abc..."
  }
}