Transcripts

Transcripts cover the recorded audio of a call. Each turn is labeled agent, prospect or gatekeeper, with start and end times. After-call transcripts come with a summary and outcome fields, and tonality analysis when it is on. Turn transcription on in recording settings or per dial session. The live transcript streams over POST /v1/calls/{id}/streams with content=transcript, listed under Calls.

Guide: Transcription.

Endpoints

GET	`/v1/calls/{id}/transcript`	Retrieve a transcript
GET	`/v1/transcripts`	Search transcripts
GET	`/v1/calls/{id}/summary`	Retrieve a summary
GET	`/v1/calls/{id}/tonality`	Retrieve tonality

The transcript object

Field	Type	Description
`id`	string	Unique ID, starts with trn_.
`call_id`	string	The call that was transcribed.
`recording_id`	string	The recording the transcript was made from.
`type`	string	post_call, or live when the call had transcription=live.
`status`	string	processing or ready. transcript.ready is sent when it is ready.
`language`	string	Language code, such as en-US or es-US.
`duration_seconds`	integer	Length of the transcribed audio.
`turns`	object[]	speaker (agent, prospect or gatekeeper), start_ms, end_ms and text for each turn.
`redactions`	integer	Spoken card numbers removed from the text.
`created_at`	string	When the transcript was ready, ISO 8601.

Retrieve a transcript

Returns the transcript of a call. Only the recorded audio is transcribed, so on an all-party call the lead's turns start after consent.

GET/v1/calls/{id}/transcript

GET/v1/calls/{id}/transcript

curl https://api.liveleg.dev/v1/calls/cal_8Jq2mT4x/transcript \
  -H "Authorization: Bearer $LIVELEG_API_KEY"

const res = await fetch('https://api.liveleg.dev/v1/calls/cal_8Jq2mT4x/transcript', {
  method: 'GET',
  headers: {
    Authorization: `Bearer ${process.env.LIVELEG_API_KEY}`,
  },
});
const data = await res.json();

import os, requests

data = requests.get(
    "https://api.liveleg.dev/v1/calls/cal_8Jq2mT4x/transcript",
    headers={"Authorization": f"Bearer {os.environ['LIVELEG_API_KEY']}"},
).json()

Response

{
  "id": "trn_5Vb20Qe",
  "object": "transcript",
  "call_id": "cal_8Jq2mT4x",
  "recording_id": "rec_0Hy3k",
  "type": "post_call",
  "status": "ready",
  "language": "en-US",
  "duration_seconds": 262,
  "turns": [
    {
      "speaker": "agent",
      "start_ms": 0,
      "end_ms": 4210,
      "text": "Hi, this is Sam with Ridgeline Roofing. Is this the owner?"
    },
    {
      "speaker": "prospect",
      "start_ms": 4630,
      "end_ms": 6020,
      "text": "Yes, this is Dana."
    },
    {
      "speaker": "agent",
      "start_ms": 6400,
      "end_ms": 11870,
      "text": "We did a few roofs on your street after the hail last week. Can I set up a free inspection?"
    },
    {
      "speaker": "prospect",
      "start_ms": 12310,
      "end_ms": 16050,
      "text": "I am on a job right now. Call me Thursday after 2."
    }
  ],
  "redactions": 1,
  "created_at": "2026-11-03T15:46:58Z"
}

Search transcripts

Finds calls whose transcripts contain the words or phrase you send. Each result lists the matching turns with their times. Results are newest first.

GET/v1/transcripts

Query parameters	Type	Description
`query`required	string	Words or a phrase in quotes.
`speaker`	string	Only turns by agent, prospect or gatekeeper.
`agent_id`	string	Only calls taken by this agent.
`outcome`	string	Only calls with this outcome.
`created_after`	string	ISO 8601.
`created_before`	string	ISO 8601.
`limit`	integer	1 to 100. Default 20.
`starting_after`	string	The last ID from the previous page.

GET/v1/transcripts

curl "https://api.liveleg.dev/v1/transcripts?query=%22roof+inspection%22&speaker=prospect&outcome=interested" \
  -H "Authorization: Bearer $LIVELEG_API_KEY"

const res = await fetch('https://api.liveleg.dev/v1/transcripts?query=%22roof+inspection%22&speaker=prospect&outcome=interested', {
  method: 'GET',
  headers: {
    Authorization: `Bearer ${process.env.LIVELEG_API_KEY}`,
  },
});
const data = await res.json();

import os, requests

data = requests.get(
    "https://api.liveleg.dev/v1/transcripts",
    headers={"Authorization": f"Bearer {os.environ['LIVELEG_API_KEY']}"},
    params={
        "query": "\"roof inspection\"",
        "speaker": "prospect",
        "outcome": "interested",
    },
).json()

Response

{
  "object": "list",
  "data": [
    {
      "call_id": "cal_7Hd1aP2c",
      "agent_id": "agt_114",
      "lead_id": "led_9Pq1",
      "outcome": "interested",
      "matches": [
        {
          "speaker": "prospect",
          "start_ms": 48210,
          "text": "We could do the roof inspection next week."
        }
      ]
    }
  ],
  "has_more": false
}

Retrieve a summary

Returns the summary and outcome fields of an after-call transcript. summary.ready is sent when they are ready. outcome is interested, callback_requested, not_interested, do_not_call, wrong_number, gatekeeper or no_conversation. When the lead asks not to be called again, the number goes on your do-not-call list, outcome is do_not_call and opt_out_requested is true. callback_at does not schedule a call. Send it as a disposition to schedule one.

GET/v1/calls/{id}/summary

GET/v1/calls/{id}/summary

curl https://api.liveleg.dev/v1/calls/cal_8Jq2mT4x/summary \
  -H "Authorization: Bearer $LIVELEG_API_KEY"

const res = await fetch('https://api.liveleg.dev/v1/calls/cal_8Jq2mT4x/summary', {
  method: 'GET',
  headers: {
    Authorization: `Bearer ${process.env.LIVELEG_API_KEY}`,
  },
});
const data = await res.json();

import os, requests

data = requests.get(
    "https://api.liveleg.dev/v1/calls/cal_8Jq2mT4x/summary",
    headers={"Authorization": f"Bearer {os.environ['LIVELEG_API_KEY']}"},
).json()

Response

{
  "object": "call_summary",
  "call_id": "cal_8Jq2mT4x",
  "transcript_id": "trn_5Vb20Qe",
  "summary": "Owner answered. Busy on a job, asked for a call Thursday after 2 pm.",
  "outcome": "callback_requested",
  "callback_at": "2026-11-06T14:00:00-06:00",
  "opt_out_requested": false,
  "created_at": "2026-11-03T15:47:02Z"
}

Retrieve tonality

Returns tone, energy, sentiment and talk/listen ratio for each speaker. Runs on transcribed calls when tonality is true in recording settings. tonality.ready is sent when it is ready. tone is friendly, neutral, tense or flat, for most of the call. energy is 0 to 1, from voice volume and pace. sentiment is -1 to 1, from words and voice. talk_ratio is the share of the call's talk time spoken by the speaker.

GET/v1/calls/{id}/tonality

GET/v1/calls/{id}/tonality

curl https://api.liveleg.dev/v1/calls/cal_8Jq2mT4x/tonality \
  -H "Authorization: Bearer $LIVELEG_API_KEY"

const res = await fetch('https://api.liveleg.dev/v1/calls/cal_8Jq2mT4x/tonality', {
  method: 'GET',
  headers: {
    Authorization: `Bearer ${process.env.LIVELEG_API_KEY}`,
  },
});
const data = await res.json();

import os, requests

data = requests.get(
    "https://api.liveleg.dev/v1/calls/cal_8Jq2mT4x/tonality",
    headers={"Authorization": f"Bearer {os.environ['LIVELEG_API_KEY']}"},
).json()

Response

{
  "object": "tonality",
  "call_id": "cal_8Jq2mT4x",
  "transcript_id": "trn_5Vb20Qe",
  "speakers": [
    {
      "speaker": "agent",
      "tone": "friendly",
      "energy": 0.68,
      "sentiment": 0.42,
      "talk_ratio": 0.57
    },
    {
      "speaker": "prospect",
      "tone": "neutral",
      "energy": 0.51,
      "sentiment": 0.18,
      "talk_ratio": 0.43
    }
  ],
  "created_at": "2026-11-03T15:47:09Z"
}