Create Call

curl --request POST \
  --url https://api.usetuner.ai/api/v1/public/call \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "call_id": "<string>",
  "call_type": "<string>",
  "transcript_with_tool_calls": [
    {
      "text": "<string>",
      "words": [
        {
          "word": "<string>",
          "start_ms": 123,
          "end_ms": 123,
          "confidence": 123
        }
      ],
      "start_ms": 123,
      "end_ms": 123,
      "duration_ms": 123,
      "node": {
        "to": "<string>",
        "from": "<string>",
        "reason": "<string>"
      },
      "tool": {
        "name": "<string>",
        "request_id": "<string>",
        "params": {},
        "result": {},
        "is_error": true,
        "error": "<string>",
        "start_ms": 123,
        "end_ms": 123
      },
      "metadata": {
        "e2e_latency": 123,
        "interrupted": true,
        "llm_node_ttft": 123,
        "tts_node_ttfb": 123,
        "transcript_confidence": 123,
        "stt_node_ttfb": 123,
        "eou_delay": 123
      }
    }
  ],
  "start_timestamp": 123,
  "end_timestamp": 123,
  "recording_url": "<string>",
  "sip_call_id": "<string>",
  "recipient": "<string>",
  "agent_version": 1,
  "transcript": "<string>",
  "duration_ms": 123,
  "call_status": "<string>",
  "disconnection_reason": "<string>",
  "caller_phone_number": "<string>",
  "call_successful": true,
  "user_sentiment": "<string>",
  "in_voicemail": true,
  "collected_dynamic_variables": {},
  "call_cost": 123,
  "call_analysis": {},
  "metadata": {
    "ai_models": {
      "asr_model": "<string>",
      "llm_model": "<string>",
      "tts_model": "<string>"
    },
    "usage_token": {
      "stt_duration_seconds": 123,
      "llm_token": 123,
      "tts_characters_count": 123
    }
  },
  "general_meta_data_raw": {},
  "recording_multi_channel_url": "<string>",
  "recording_file_extension": "<string>",
  "recording_s3_multi_channel": true,
  "recording_s3_caller_channel": 1
}
'

import requests

url = "https://api.usetuner.ai/api/v1/public/call"

payload = {
    "call_id": "<string>",
    "call_type": "<string>",
    "transcript_with_tool_calls": [
        {
            "text": "<string>",
            "words": [
                {
                    "word": "<string>",
                    "start_ms": 123,
                    "end_ms": 123,
                    "confidence": 123
                }
            ],
            "start_ms": 123,
            "end_ms": 123,
            "duration_ms": 123,
            "node": {
                "to": "<string>",
                "from": "<string>",
                "reason": "<string>"
            },
            "tool": {
                "name": "<string>",
                "request_id": "<string>",
                "params": {},
                "result": {},
                "is_error": True,
                "error": "<string>",
                "start_ms": 123,
                "end_ms": 123
            },
            "metadata": {
                "e2e_latency": 123,
                "interrupted": True,
                "llm_node_ttft": 123,
                "tts_node_ttfb": 123,
                "transcript_confidence": 123,
                "stt_node_ttfb": 123,
                "eou_delay": 123
            }
        }
    ],
    "start_timestamp": 123,
    "end_timestamp": 123,
    "recording_url": "<string>",
    "sip_call_id": "<string>",
    "recipient": "<string>",
    "agent_version": 1,
    "transcript": "<string>",
    "duration_ms": 123,
    "call_status": "<string>",
    "disconnection_reason": "<string>",
    "caller_phone_number": "<string>",
    "call_successful": True,
    "user_sentiment": "<string>",
    "in_voicemail": True,
    "collected_dynamic_variables": {},
    "call_cost": 123,
    "call_analysis": {},
    "metadata": {
        "ai_models": {
            "asr_model": "<string>",
            "llm_model": "<string>",
            "tts_model": "<string>"
        },
        "usage_token": {
            "stt_duration_seconds": 123,
            "llm_token": 123,
            "tts_characters_count": 123
        }
    },
    "general_meta_data_raw": {},
    "recording_multi_channel_url": "<string>",
    "recording_file_extension": "<string>",
    "recording_s3_multi_channel": True,
    "recording_s3_caller_channel": 1
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    call_id: '<string>',
    call_type: '<string>',
    transcript_with_tool_calls: [
      {
        text: '<string>',
        words: [{word: '<string>', start_ms: 123, end_ms: 123, confidence: 123}],
        start_ms: 123,
        end_ms: 123,
        duration_ms: 123,
        node: {to: '<string>', from: '<string>', reason: '<string>'},
        tool: {
          name: '<string>',
          request_id: '<string>',
          params: {},
          result: {},
          is_error: true,
          error: '<string>',
          start_ms: 123,
          end_ms: 123
        },
        metadata: {
          e2e_latency: 123,
          interrupted: true,
          llm_node_ttft: 123,
          tts_node_ttfb: 123,
          transcript_confidence: 123,
          stt_node_ttfb: 123,
          eou_delay: 123
        }
      }
    ],
    start_timestamp: 123,
    end_timestamp: 123,
    recording_url: '<string>',
    sip_call_id: '<string>',
    recipient: '<string>',
    agent_version: 1,
    transcript: '<string>',
    duration_ms: 123,
    call_status: '<string>',
    disconnection_reason: '<string>',
    caller_phone_number: '<string>',
    call_successful: true,
    user_sentiment: '<string>',
    in_voicemail: true,
    collected_dynamic_variables: {},
    call_cost: 123,
    call_analysis: {},
    metadata: {
      ai_models: {asr_model: '<string>', llm_model: '<string>', tts_model: '<string>'},
      usage_token: {stt_duration_seconds: 123, llm_token: 123, tts_characters_count: 123}
    },
    general_meta_data_raw: {},
    recording_multi_channel_url: '<string>',
    recording_file_extension: '<string>',
    recording_s3_multi_channel: true,
    recording_s3_caller_channel: 1
  })
};

fetch('https://api.usetuner.ai/api/v1/public/call', 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.usetuner.ai/api/v1/public/call",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'call_id' => '<string>',
    'call_type' => '<string>',
    'transcript_with_tool_calls' => [
        [
                'text' => '<string>',
                'words' => [
                                [
                                                                'word' => '<string>',
                                                                'start_ms' => 123,
                                                                'end_ms' => 123,
                                                                'confidence' => 123
                                ]
                ],
                'start_ms' => 123,
                'end_ms' => 123,
                'duration_ms' => 123,
                'node' => [
                                'to' => '<string>',
                                'from' => '<string>',
                                'reason' => '<string>'
                ],
                'tool' => [
                                'name' => '<string>',
                                'request_id' => '<string>',
                                'params' => [
                                                                
                                ],
                                'result' => [
                                                                
                                ],
                                'is_error' => true,
                                'error' => '<string>',
                                'start_ms' => 123,
                                'end_ms' => 123
                ],
                'metadata' => [
                                'e2e_latency' => 123,
                                'interrupted' => true,
                                'llm_node_ttft' => 123,
                                'tts_node_ttfb' => 123,
                                'transcript_confidence' => 123,
                                'stt_node_ttfb' => 123,
                                'eou_delay' => 123
                ]
        ]
    ],
    'start_timestamp' => 123,
    'end_timestamp' => 123,
    'recording_url' => '<string>',
    'sip_call_id' => '<string>',
    'recipient' => '<string>',
    'agent_version' => 1,
    'transcript' => '<string>',
    'duration_ms' => 123,
    'call_status' => '<string>',
    'disconnection_reason' => '<string>',
    'caller_phone_number' => '<string>',
    'call_successful' => true,
    'user_sentiment' => '<string>',
    'in_voicemail' => true,
    'collected_dynamic_variables' => [
        
    ],
    'call_cost' => 123,
    'call_analysis' => [
        
    ],
    'metadata' => [
        'ai_models' => [
                'asr_model' => '<string>',
                'llm_model' => '<string>',
                'tts_model' => '<string>'
        ],
        'usage_token' => [
                'stt_duration_seconds' => 123,
                'llm_token' => 123,
                'tts_characters_count' => 123
        ]
    ],
    'general_meta_data_raw' => [
        
    ],
    'recording_multi_channel_url' => '<string>',
    'recording_file_extension' => '<string>',
    'recording_s3_multi_channel' => true,
    'recording_s3_caller_channel' => 1
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>",
    "Content-Type: application/json"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

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

func main() {

	url := "https://api.usetuner.ai/api/v1/public/call"

	payload := strings.NewReader("{\n  \"call_id\": \"<string>\",\n  \"call_type\": \"<string>\",\n  \"transcript_with_tool_calls\": [\n    {\n      \"text\": \"<string>\",\n      \"words\": [\n        {\n          \"word\": \"<string>\",\n          \"start_ms\": 123,\n          \"end_ms\": 123,\n          \"confidence\": 123\n        }\n      ],\n      \"start_ms\": 123,\n      \"end_ms\": 123,\n      \"duration_ms\": 123,\n      \"node\": {\n        \"to\": \"<string>\",\n        \"from\": \"<string>\",\n        \"reason\": \"<string>\"\n      },\n      \"tool\": {\n        \"name\": \"<string>\",\n        \"request_id\": \"<string>\",\n        \"params\": {},\n        \"result\": {},\n        \"is_error\": true,\n        \"error\": \"<string>\",\n        \"start_ms\": 123,\n        \"end_ms\": 123\n      },\n      \"metadata\": {\n        \"e2e_latency\": 123,\n        \"interrupted\": true,\n        \"llm_node_ttft\": 123,\n        \"tts_node_ttfb\": 123,\n        \"transcript_confidence\": 123,\n        \"stt_node_ttfb\": 123,\n        \"eou_delay\": 123\n      }\n    }\n  ],\n  \"start_timestamp\": 123,\n  \"end_timestamp\": 123,\n  \"recording_url\": \"<string>\",\n  \"sip_call_id\": \"<string>\",\n  \"recipient\": \"<string>\",\n  \"agent_version\": 1,\n  \"transcript\": \"<string>\",\n  \"duration_ms\": 123,\n  \"call_status\": \"<string>\",\n  \"disconnection_reason\": \"<string>\",\n  \"caller_phone_number\": \"<string>\",\n  \"call_successful\": true,\n  \"user_sentiment\": \"<string>\",\n  \"in_voicemail\": true,\n  \"collected_dynamic_variables\": {},\n  \"call_cost\": 123,\n  \"call_analysis\": {},\n  \"metadata\": {\n    \"ai_models\": {\n      \"asr_model\": \"<string>\",\n      \"llm_model\": \"<string>\",\n      \"tts_model\": \"<string>\"\n    },\n    \"usage_token\": {\n      \"stt_duration_seconds\": 123,\n      \"llm_token\": 123,\n      \"tts_characters_count\": 123\n    }\n  },\n  \"general_meta_data_raw\": {},\n  \"recording_multi_channel_url\": \"<string>\",\n  \"recording_file_extension\": \"<string>\",\n  \"recording_s3_multi_channel\": true,\n  \"recording_s3_caller_channel\": 1\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Authorization", "Bearer <token>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://api.usetuner.ai/api/v1/public/call")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"call_id\": \"<string>\",\n  \"call_type\": \"<string>\",\n  \"transcript_with_tool_calls\": [\n    {\n      \"text\": \"<string>\",\n      \"words\": [\n        {\n          \"word\": \"<string>\",\n          \"start_ms\": 123,\n          \"end_ms\": 123,\n          \"confidence\": 123\n        }\n      ],\n      \"start_ms\": 123,\n      \"end_ms\": 123,\n      \"duration_ms\": 123,\n      \"node\": {\n        \"to\": \"<string>\",\n        \"from\": \"<string>\",\n        \"reason\": \"<string>\"\n      },\n      \"tool\": {\n        \"name\": \"<string>\",\n        \"request_id\": \"<string>\",\n        \"params\": {},\n        \"result\": {},\n        \"is_error\": true,\n        \"error\": \"<string>\",\n        \"start_ms\": 123,\n        \"end_ms\": 123\n      },\n      \"metadata\": {\n        \"e2e_latency\": 123,\n        \"interrupted\": true,\n        \"llm_node_ttft\": 123,\n        \"tts_node_ttfb\": 123,\n        \"transcript_confidence\": 123,\n        \"stt_node_ttfb\": 123,\n        \"eou_delay\": 123\n      }\n    }\n  ],\n  \"start_timestamp\": 123,\n  \"end_timestamp\": 123,\n  \"recording_url\": \"<string>\",\n  \"sip_call_id\": \"<string>\",\n  \"recipient\": \"<string>\",\n  \"agent_version\": 1,\n  \"transcript\": \"<string>\",\n  \"duration_ms\": 123,\n  \"call_status\": \"<string>\",\n  \"disconnection_reason\": \"<string>\",\n  \"caller_phone_number\": \"<string>\",\n  \"call_successful\": true,\n  \"user_sentiment\": \"<string>\",\n  \"in_voicemail\": true,\n  \"collected_dynamic_variables\": {},\n  \"call_cost\": 123,\n  \"call_analysis\": {},\n  \"metadata\": {\n    \"ai_models\": {\n      \"asr_model\": \"<string>\",\n      \"llm_model\": \"<string>\",\n      \"tts_model\": \"<string>\"\n    },\n    \"usage_token\": {\n      \"stt_duration_seconds\": 123,\n      \"llm_token\": 123,\n      \"tts_characters_count\": 123\n    }\n  },\n  \"general_meta_data_raw\": {},\n  \"recording_multi_channel_url\": \"<string>\",\n  \"recording_file_extension\": \"<string>\",\n  \"recording_s3_multi_channel\": true,\n  \"recording_s3_caller_channel\": 1\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.usetuner.ai/api/v1/public/call")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"call_id\": \"<string>\",\n  \"call_type\": \"<string>\",\n  \"transcript_with_tool_calls\": [\n    {\n      \"text\": \"<string>\",\n      \"words\": [\n        {\n          \"word\": \"<string>\",\n          \"start_ms\": 123,\n          \"end_ms\": 123,\n          \"confidence\": 123\n        }\n      ],\n      \"start_ms\": 123,\n      \"end_ms\": 123,\n      \"duration_ms\": 123,\n      \"node\": {\n        \"to\": \"<string>\",\n        \"from\": \"<string>\",\n        \"reason\": \"<string>\"\n      },\n      \"tool\": {\n        \"name\": \"<string>\",\n        \"request_id\": \"<string>\",\n        \"params\": {},\n        \"result\": {},\n        \"is_error\": true,\n        \"error\": \"<string>\",\n        \"start_ms\": 123,\n        \"end_ms\": 123\n      },\n      \"metadata\": {\n        \"e2e_latency\": 123,\n        \"interrupted\": true,\n        \"llm_node_ttft\": 123,\n        \"tts_node_ttfb\": 123,\n        \"transcript_confidence\": 123,\n        \"stt_node_ttfb\": 123,\n        \"eou_delay\": 123\n      }\n    }\n  ],\n  \"start_timestamp\": 123,\n  \"end_timestamp\": 123,\n  \"recording_url\": \"<string>\",\n  \"sip_call_id\": \"<string>\",\n  \"recipient\": \"<string>\",\n  \"agent_version\": 1,\n  \"transcript\": \"<string>\",\n  \"duration_ms\": 123,\n  \"call_status\": \"<string>\",\n  \"disconnection_reason\": \"<string>\",\n  \"caller_phone_number\": \"<string>\",\n  \"call_successful\": true,\n  \"user_sentiment\": \"<string>\",\n  \"in_voicemail\": true,\n  \"collected_dynamic_variables\": {},\n  \"call_cost\": 123,\n  \"call_analysis\": {},\n  \"metadata\": {\n    \"ai_models\": {\n      \"asr_model\": \"<string>\",\n      \"llm_model\": \"<string>\",\n      \"tts_model\": \"<string>\"\n    },\n    \"usage_token\": {\n      \"stt_duration_seconds\": 123,\n      \"llm_token\": 123,\n      \"tts_characters_count\": 123\n    }\n  },\n  \"general_meta_data_raw\": {},\n  \"recording_multi_channel_url\": \"<string>\",\n  \"recording_file_extension\": \"<string>\",\n  \"recording_s3_multi_channel\": true,\n  \"recording_s3_caller_channel\": 1\n}"

response = http.request(request)
puts response.read_body

{
  "id": 123,
  "provider_call_id": "<string>",
  "is_new": true,
  "recording_upload": {
    "url": "<string>",
    "fields": {},
    "key": "<string>",
    "content_type": "<string>",
    "max_bytes": 123,
    "expires_at": "2023-11-07T05:31:56Z"
  }
}

{
  "detail": "end_timestamp must be after start_timestamp"
}

{
  "detail": "Not authenticated"
}

{
  "detail": "Workspace has insufficient credits"
}

{
  "detail": "User does not have access to workspace 42"
}

{
  "detail": "Agent with remote identifier agent_abc123 not found"
}

{
  "detail": "Call with ID call_abc123 already exists for provider 4"
}

{
  "detail": [
    {
      "loc": [
        "<string>"
      ],
      "msg": "<string>",
      "type": "<string>",
      "input": "<unknown>",
      "ctx": {}
    }
  ]
}

{
  "detail": "Rate limit exceeded: 60 requests per minute allowed for this workspace."
}

{
  "detail": "Failed to create call"
}

{
  "detail": "Recording uploads are not available in this environment."
}

Calls

Create Call

Ingest a completed call for analysis.

Accepts the transcript and metadata for a call that has already finished on your platform. Tuner queues it for evaluation; scores, outcomes, and red flags appear on the call record shortly after.

call_id must be unique. Re-sending a call that’s already been ingested returns a conflict rather than replacing it.

Supplying recording_file_extension opts a newly-created call into a presigned upload flow: the response’s recording_upload carries an S3 POST target the caller can upload the recording audio to directly, valid for 24 hours. This is a deployment-level opt-in, not just a per-request one — an environment with no upload signer configured rejects the request outright (503) rather than silently omitting the upload target, so a caller relying on it finds out immediately rather than discovering a null recording_upload later.

If the audio uploaded via recording_file_extension has the caller and the agent on separate channels, set recording_s3_multi_channel: true; if the caller isn’t on channel 0, also set recording_s3_caller_channel to the caller’s channel index.

POST

api

public

call

Create Call

curl --request POST \
  --url https://api.usetuner.ai/api/v1/public/call \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "call_id": "<string>",
  "call_type": "<string>",
  "transcript_with_tool_calls": [
    {
      "text": "<string>",
      "words": [
        {
          "word": "<string>",
          "start_ms": 123,
          "end_ms": 123,
          "confidence": 123
        }
      ],
      "start_ms": 123,
      "end_ms": 123,
      "duration_ms": 123,
      "node": {
        "to": "<string>",
        "from": "<string>",
        "reason": "<string>"
      },
      "tool": {
        "name": "<string>",
        "request_id": "<string>",
        "params": {},
        "result": {},
        "is_error": true,
        "error": "<string>",
        "start_ms": 123,
        "end_ms": 123
      },
      "metadata": {
        "e2e_latency": 123,
        "interrupted": true,
        "llm_node_ttft": 123,
        "tts_node_ttfb": 123,
        "transcript_confidence": 123,
        "stt_node_ttfb": 123,
        "eou_delay": 123
      }
    }
  ],
  "start_timestamp": 123,
  "end_timestamp": 123,
  "recording_url": "<string>",
  "sip_call_id": "<string>",
  "recipient": "<string>",
  "agent_version": 1,
  "transcript": "<string>",
  "duration_ms": 123,
  "call_status": "<string>",
  "disconnection_reason": "<string>",
  "caller_phone_number": "<string>",
  "call_successful": true,
  "user_sentiment": "<string>",
  "in_voicemail": true,
  "collected_dynamic_variables": {},
  "call_cost": 123,
  "call_analysis": {},
  "metadata": {
    "ai_models": {
      "asr_model": "<string>",
      "llm_model": "<string>",
      "tts_model": "<string>"
    },
    "usage_token": {
      "stt_duration_seconds": 123,
      "llm_token": 123,
      "tts_characters_count": 123
    }
  },
  "general_meta_data_raw": {},
  "recording_multi_channel_url": "<string>",
  "recording_file_extension": "<string>",
  "recording_s3_multi_channel": true,
  "recording_s3_caller_channel": 1
}
'

import requests

url = "https://api.usetuner.ai/api/v1/public/call"

payload = {
    "call_id": "<string>",
    "call_type": "<string>",
    "transcript_with_tool_calls": [
        {
            "text": "<string>",
            "words": [
                {
                    "word": "<string>",
                    "start_ms": 123,
                    "end_ms": 123,
                    "confidence": 123
                }
            ],
            "start_ms": 123,
            "end_ms": 123,
            "duration_ms": 123,
            "node": {
                "to": "<string>",
                "from": "<string>",
                "reason": "<string>"
            },
            "tool": {
                "name": "<string>",
                "request_id": "<string>",
                "params": {},
                "result": {},
                "is_error": True,
                "error": "<string>",
                "start_ms": 123,
                "end_ms": 123
            },
            "metadata": {
                "e2e_latency": 123,
                "interrupted": True,
                "llm_node_ttft": 123,
                "tts_node_ttfb": 123,
                "transcript_confidence": 123,
                "stt_node_ttfb": 123,
                "eou_delay": 123
            }
        }
    ],
    "start_timestamp": 123,
    "end_timestamp": 123,
    "recording_url": "<string>",
    "sip_call_id": "<string>",
    "recipient": "<string>",
    "agent_version": 1,
    "transcript": "<string>",
    "duration_ms": 123,
    "call_status": "<string>",
    "disconnection_reason": "<string>",
    "caller_phone_number": "<string>",
    "call_successful": True,
    "user_sentiment": "<string>",
    "in_voicemail": True,
    "collected_dynamic_variables": {},
    "call_cost": 123,
    "call_analysis": {},
    "metadata": {
        "ai_models": {
            "asr_model": "<string>",
            "llm_model": "<string>",
            "tts_model": "<string>"
        },
        "usage_token": {
            "stt_duration_seconds": 123,
            "llm_token": 123,
            "tts_characters_count": 123
        }
    },
    "general_meta_data_raw": {},
    "recording_multi_channel_url": "<string>",
    "recording_file_extension": "<string>",
    "recording_s3_multi_channel": True,
    "recording_s3_caller_channel": 1
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    call_id: '<string>',
    call_type: '<string>',
    transcript_with_tool_calls: [
      {
        text: '<string>',
        words: [{word: '<string>', start_ms: 123, end_ms: 123, confidence: 123}],
        start_ms: 123,
        end_ms: 123,
        duration_ms: 123,
        node: {to: '<string>', from: '<string>', reason: '<string>'},
        tool: {
          name: '<string>',
          request_id: '<string>',
          params: {},
          result: {},
          is_error: true,
          error: '<string>',
          start_ms: 123,
          end_ms: 123
        },
        metadata: {
          e2e_latency: 123,
          interrupted: true,
          llm_node_ttft: 123,
          tts_node_ttfb: 123,
          transcript_confidence: 123,
          stt_node_ttfb: 123,
          eou_delay: 123
        }
      }
    ],
    start_timestamp: 123,
    end_timestamp: 123,
    recording_url: '<string>',
    sip_call_id: '<string>',
    recipient: '<string>',
    agent_version: 1,
    transcript: '<string>',
    duration_ms: 123,
    call_status: '<string>',
    disconnection_reason: '<string>',
    caller_phone_number: '<string>',
    call_successful: true,
    user_sentiment: '<string>',
    in_voicemail: true,
    collected_dynamic_variables: {},
    call_cost: 123,
    call_analysis: {},
    metadata: {
      ai_models: {asr_model: '<string>', llm_model: '<string>', tts_model: '<string>'},
      usage_token: {stt_duration_seconds: 123, llm_token: 123, tts_characters_count: 123}
    },
    general_meta_data_raw: {},
    recording_multi_channel_url: '<string>',
    recording_file_extension: '<string>',
    recording_s3_multi_channel: true,
    recording_s3_caller_channel: 1
  })
};

fetch('https://api.usetuner.ai/api/v1/public/call', 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.usetuner.ai/api/v1/public/call",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'call_id' => '<string>',
    'call_type' => '<string>',
    'transcript_with_tool_calls' => [
        [
                'text' => '<string>',
                'words' => [
                                [
                                                                'word' => '<string>',
                                                                'start_ms' => 123,
                                                                'end_ms' => 123,
                                                                'confidence' => 123
                                ]
                ],
                'start_ms' => 123,
                'end_ms' => 123,
                'duration_ms' => 123,
                'node' => [
                                'to' => '<string>',
                                'from' => '<string>',
                                'reason' => '<string>'
                ],
                'tool' => [
                                'name' => '<string>',
                                'request_id' => '<string>',
                                'params' => [
                                                                
                                ],
                                'result' => [
                                                                
                                ],
                                'is_error' => true,
                                'error' => '<string>',
                                'start_ms' => 123,
                                'end_ms' => 123
                ],
                'metadata' => [
                                'e2e_latency' => 123,
                                'interrupted' => true,
                                'llm_node_ttft' => 123,
                                'tts_node_ttfb' => 123,
                                'transcript_confidence' => 123,
                                'stt_node_ttfb' => 123,
                                'eou_delay' => 123
                ]
        ]
    ],
    'start_timestamp' => 123,
    'end_timestamp' => 123,
    'recording_url' => '<string>',
    'sip_call_id' => '<string>',
    'recipient' => '<string>',
    'agent_version' => 1,
    'transcript' => '<string>',
    'duration_ms' => 123,
    'call_status' => '<string>',
    'disconnection_reason' => '<string>',
    'caller_phone_number' => '<string>',
    'call_successful' => true,
    'user_sentiment' => '<string>',
    'in_voicemail' => true,
    'collected_dynamic_variables' => [
        
    ],
    'call_cost' => 123,
    'call_analysis' => [
        
    ],
    'metadata' => [
        'ai_models' => [
                'asr_model' => '<string>',
                'llm_model' => '<string>',
                'tts_model' => '<string>'
        ],
        'usage_token' => [
                'stt_duration_seconds' => 123,
                'llm_token' => 123,
                'tts_characters_count' => 123
        ]
    ],
    'general_meta_data_raw' => [
        
    ],
    'recording_multi_channel_url' => '<string>',
    'recording_file_extension' => '<string>',
    'recording_s3_multi_channel' => true,
    'recording_s3_caller_channel' => 1
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>",
    "Content-Type: application/json"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

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

func main() {

	url := "https://api.usetuner.ai/api/v1/public/call"

	payload := strings.NewReader("{\n  \"call_id\": \"<string>\",\n  \"call_type\": \"<string>\",\n  \"transcript_with_tool_calls\": [\n    {\n      \"text\": \"<string>\",\n      \"words\": [\n        {\n          \"word\": \"<string>\",\n          \"start_ms\": 123,\n          \"end_ms\": 123,\n          \"confidence\": 123\n        }\n      ],\n      \"start_ms\": 123,\n      \"end_ms\": 123,\n      \"duration_ms\": 123,\n      \"node\": {\n        \"to\": \"<string>\",\n        \"from\": \"<string>\",\n        \"reason\": \"<string>\"\n      },\n      \"tool\": {\n        \"name\": \"<string>\",\n        \"request_id\": \"<string>\",\n        \"params\": {},\n        \"result\": {},\n        \"is_error\": true,\n        \"error\": \"<string>\",\n        \"start_ms\": 123,\n        \"end_ms\": 123\n      },\n      \"metadata\": {\n        \"e2e_latency\": 123,\n        \"interrupted\": true,\n        \"llm_node_ttft\": 123,\n        \"tts_node_ttfb\": 123,\n        \"transcript_confidence\": 123,\n        \"stt_node_ttfb\": 123,\n        \"eou_delay\": 123\n      }\n    }\n  ],\n  \"start_timestamp\": 123,\n  \"end_timestamp\": 123,\n  \"recording_url\": \"<string>\",\n  \"sip_call_id\": \"<string>\",\n  \"recipient\": \"<string>\",\n  \"agent_version\": 1,\n  \"transcript\": \"<string>\",\n  \"duration_ms\": 123,\n  \"call_status\": \"<string>\",\n  \"disconnection_reason\": \"<string>\",\n  \"caller_phone_number\": \"<string>\",\n  \"call_successful\": true,\n  \"user_sentiment\": \"<string>\",\n  \"in_voicemail\": true,\n  \"collected_dynamic_variables\": {},\n  \"call_cost\": 123,\n  \"call_analysis\": {},\n  \"metadata\": {\n    \"ai_models\": {\n      \"asr_model\": \"<string>\",\n      \"llm_model\": \"<string>\",\n      \"tts_model\": \"<string>\"\n    },\n    \"usage_token\": {\n      \"stt_duration_seconds\": 123,\n      \"llm_token\": 123,\n      \"tts_characters_count\": 123\n    }\n  },\n  \"general_meta_data_raw\": {},\n  \"recording_multi_channel_url\": \"<string>\",\n  \"recording_file_extension\": \"<string>\",\n  \"recording_s3_multi_channel\": true,\n  \"recording_s3_caller_channel\": 1\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Authorization", "Bearer <token>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://api.usetuner.ai/api/v1/public/call")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"call_id\": \"<string>\",\n  \"call_type\": \"<string>\",\n  \"transcript_with_tool_calls\": [\n    {\n      \"text\": \"<string>\",\n      \"words\": [\n        {\n          \"word\": \"<string>\",\n          \"start_ms\": 123,\n          \"end_ms\": 123,\n          \"confidence\": 123\n        }\n      ],\n      \"start_ms\": 123,\n      \"end_ms\": 123,\n      \"duration_ms\": 123,\n      \"node\": {\n        \"to\": \"<string>\",\n        \"from\": \"<string>\",\n        \"reason\": \"<string>\"\n      },\n      \"tool\": {\n        \"name\": \"<string>\",\n        \"request_id\": \"<string>\",\n        \"params\": {},\n        \"result\": {},\n        \"is_error\": true,\n        \"error\": \"<string>\",\n        \"start_ms\": 123,\n        \"end_ms\": 123\n      },\n      \"metadata\": {\n        \"e2e_latency\": 123,\n        \"interrupted\": true,\n        \"llm_node_ttft\": 123,\n        \"tts_node_ttfb\": 123,\n        \"transcript_confidence\": 123,\n        \"stt_node_ttfb\": 123,\n        \"eou_delay\": 123\n      }\n    }\n  ],\n  \"start_timestamp\": 123,\n  \"end_timestamp\": 123,\n  \"recording_url\": \"<string>\",\n  \"sip_call_id\": \"<string>\",\n  \"recipient\": \"<string>\",\n  \"agent_version\": 1,\n  \"transcript\": \"<string>\",\n  \"duration_ms\": 123,\n  \"call_status\": \"<string>\",\n  \"disconnection_reason\": \"<string>\",\n  \"caller_phone_number\": \"<string>\",\n  \"call_successful\": true,\n  \"user_sentiment\": \"<string>\",\n  \"in_voicemail\": true,\n  \"collected_dynamic_variables\": {},\n  \"call_cost\": 123,\n  \"call_analysis\": {},\n  \"metadata\": {\n    \"ai_models\": {\n      \"asr_model\": \"<string>\",\n      \"llm_model\": \"<string>\",\n      \"tts_model\": \"<string>\"\n    },\n    \"usage_token\": {\n      \"stt_duration_seconds\": 123,\n      \"llm_token\": 123,\n      \"tts_characters_count\": 123\n    }\n  },\n  \"general_meta_data_raw\": {},\n  \"recording_multi_channel_url\": \"<string>\",\n  \"recording_file_extension\": \"<string>\",\n  \"recording_s3_multi_channel\": true,\n  \"recording_s3_caller_channel\": 1\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.usetuner.ai/api/v1/public/call")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"call_id\": \"<string>\",\n  \"call_type\": \"<string>\",\n  \"transcript_with_tool_calls\": [\n    {\n      \"text\": \"<string>\",\n      \"words\": [\n        {\n          \"word\": \"<string>\",\n          \"start_ms\": 123,\n          \"end_ms\": 123,\n          \"confidence\": 123\n        }\n      ],\n      \"start_ms\": 123,\n      \"end_ms\": 123,\n      \"duration_ms\": 123,\n      \"node\": {\n        \"to\": \"<string>\",\n        \"from\": \"<string>\",\n        \"reason\": \"<string>\"\n      },\n      \"tool\": {\n        \"name\": \"<string>\",\n        \"request_id\": \"<string>\",\n        \"params\": {},\n        \"result\": {},\n        \"is_error\": true,\n        \"error\": \"<string>\",\n        \"start_ms\": 123,\n        \"end_ms\": 123\n      },\n      \"metadata\": {\n        \"e2e_latency\": 123,\n        \"interrupted\": true,\n        \"llm_node_ttft\": 123,\n        \"tts_node_ttfb\": 123,\n        \"transcript_confidence\": 123,\n        \"stt_node_ttfb\": 123,\n        \"eou_delay\": 123\n      }\n    }\n  ],\n  \"start_timestamp\": 123,\n  \"end_timestamp\": 123,\n  \"recording_url\": \"<string>\",\n  \"sip_call_id\": \"<string>\",\n  \"recipient\": \"<string>\",\n  \"agent_version\": 1,\n  \"transcript\": \"<string>\",\n  \"duration_ms\": 123,\n  \"call_status\": \"<string>\",\n  \"disconnection_reason\": \"<string>\",\n  \"caller_phone_number\": \"<string>\",\n  \"call_successful\": true,\n  \"user_sentiment\": \"<string>\",\n  \"in_voicemail\": true,\n  \"collected_dynamic_variables\": {},\n  \"call_cost\": 123,\n  \"call_analysis\": {},\n  \"metadata\": {\n    \"ai_models\": {\n      \"asr_model\": \"<string>\",\n      \"llm_model\": \"<string>\",\n      \"tts_model\": \"<string>\"\n    },\n    \"usage_token\": {\n      \"stt_duration_seconds\": 123,\n      \"llm_token\": 123,\n      \"tts_characters_count\": 123\n    }\n  },\n  \"general_meta_data_raw\": {},\n  \"recording_multi_channel_url\": \"<string>\",\n  \"recording_file_extension\": \"<string>\",\n  \"recording_s3_multi_channel\": true,\n  \"recording_s3_caller_channel\": 1\n}"

response = http.request(request)
puts response.read_body

{
  "id": 123,
  "provider_call_id": "<string>",
  "is_new": true,
  "recording_upload": {
    "url": "<string>",
    "fields": {},
    "key": "<string>",
    "content_type": "<string>",
    "max_bytes": 123,
    "expires_at": "2023-11-07T05:31:56Z"
  }
}

{
  "detail": "end_timestamp must be after start_timestamp"
}

{
  "detail": "Not authenticated"
}

{
  "detail": "Workspace has insufficient credits"
}

{
  "detail": "User does not have access to workspace 42"
}

{
  "detail": "Agent with remote identifier agent_abc123 not found"
}

{
  "detail": "Call with ID call_abc123 already exists for provider 4"
}

{
  "detail": [
    {
      "loc": [
        "<string>"
      ],
      "msg": "<string>",
      "type": "<string>",
      "input": "<unknown>",
      "ctx": {}
    }
  ]
}

{
  "detail": "Rate limit exceeded: 60 requests per minute allowed for this workspace."
}

{
  "detail": "Failed to create call"
}

{
  "detail": "Recording uploads are not available in this environment."
}

Authorizations

Authorization

string

header

required

Use Tuner API key (tr_api_...) or user session token. Find your API key in Workspace Settings > API Keys.

Query Parameters

workspace_id

integer

required

Workspace ID. Find this in Workspace > General Settings.

agent_remote_identifier

string

required

Your Agent ID configured in Tuner. Get this value from Agent Settings > Agent Connection > Agent ID.

Body

application/json

Request schema for public call creation.

call_id

string

required

Unique call identifier from your provider (used for idempotency).

Required string length: 1 - 200

call_type

string

required

Call channel/type from your provider (e.g., 'phone_call', 'web_call').

Required string length: 1 - 100

transcript_with_tool_calls

PublicTranscriptSegment · object[]

required

The call timeline in chronological order. Each item is a user turn, an agent turn, a tool call or its result, or a workflow node transition.

User and agent turns must carry timing — as words, as start_ms and end_ms, or as start_ms and duration_ms. Latency and voice metrics are computed from it.

Minimum array length: 1

Show child attributes

start_timestamp

integer

required

Call start time as Unix epoch. Accepts either seconds or milliseconds.

end_timestamp

integer

required

Call end time as Unix epoch. Accepts either seconds or milliseconds. Must be greater than or equal to start_timestamp.

recording_url

string

required

Publicly reachable recording URL (audio file or provider recording link).

Required string length: 1 - 1024

sip_call_id

string | null

Optional SIP call identifier. When provided, it is used as provider_call_id for persistence and idempotency.

Required string length: 1 - 200

recipient

string | null

Recipient phone number (E.164) or SIP URL for outbound calls.

Required string length: 1 - 500

agent_version

integer | null

The version of the agent that handled this call (e.g. 3).

Required range: x >= 0

transcript

string | null

Diarized plain-text transcript (fallback for display/search). If omitted, we derive it from transcript_with_tool_calls when possible.

duration_ms

integer | null

Call duration in milliseconds. If omitted, we compute it from start_timestamp and end_timestamp.

call_status

string | null

Provider call status at ingest time. Preferred values: 'call_ended'.

Maximum string length: 100

disconnection_reason

string | null

Why the call ended (e.g. user_hangup, agent_hangup).

Maximum string length: 100

caller_phone_number

string | null

Caller phone number in E.164 format when available (e.g., '+14155550123').

Maximum string length: 50

call_successful

boolean | null

Whether the call was successful

user_sentiment

string | null

User sentiment label. Must be one of [positive, neutral, negative, unknown]

Maximum string length: 50

in_voicemail

boolean | null

Whether the call reached voicemail

collected_dynamic_variables

Collected Dynamic Variables · object | null

Dynamic variables collected during the call (free-form JSON)

call_cost

number | null

Total call cost in cents (e.g. 125 for $1.25). Client sends cents; frontend converts from dollars for UX.

call_analysis

Call Analysis · object | null

Provider-native analysis payload (free-form JSON; stored as-is)

metadata

CallMetadata · object | null

Call-level metadata (e.g. context, custom attributes). Supports structured ai_models and usage_token fields; extra keys are also accepted. Merged into general_meta_data_raw for storage. If both are sent, keys are merged; general_meta_data_raw keys win on collision.

Show child attributes

general_meta_data_raw

General Meta Data Raw · object | null

Use to store any extra metadata payload as a JSON object

recording_multi_channel_url

string | null

Multi-channel recording URL (separate speaker channels), if available.

Maximum string length: 1024

recording_file_extension

string | null

Supplying this opts the call into receiving a presigned upload target (recording_upload in the response) so you can upload the call's audio directly to Tuner's storage. Provide the file extension without a leading dot (e.g. 'wav', 'mp3'). Omit this field entirely if you are not uploading audio.

recording_s3_multi_channel

boolean | null

Whether the audio being uploaded has the caller and the agent on separate channels rather than mixed into a single channel. Only applies to audio uploaded via recording_file_extension. Omit this field if the recording is a mono mix -- it is treated as a mono mix by default.

recording_s3_caller_channel

integer | null

The 0-based index of the channel carrying the caller's voice, for audio uploaded via recording_file_extension. Defaults to 0 and is only meaningful when recording_s3_multi_channel is true.

Required range: x >= 0

Response

Successful Response

Response schema for public call creation.

integer

required

Internal Tuner call ID

provider_call_id

string

required

Echo of the persisted provider call ID (sip_call_id when provided, else call_id).

is_new

boolean

required

Whether the call was newly created (false means it already existed)

recording_upload

RecordingUploadTarget · object | null

Present only when the request set recording_file_extension and the upload target could be prepared. Null if the extension was omitted, if the call already had a recording uploaded, or if preparing the target failed after the call was otherwise saved successfully.

Show child attributes