# Reply in a conversation

Source: https://docs.vlayers.ai/reference/conversations/reply-to-conversation

`POST /v1/conversations/{id}/messages` · scope `messages:send`

Sends a message into an existing conversation. The channel, your sender and the recipient come from the conversation, so you only send the content. This is how your code answers someone who wrote to you.

Requires an API key with the `messages:send` scope.

| Name | In | Type | Required | Description |
|---|---|---|---|---|
| `id` | path | string | yes | The conversation id. Example: `"0192f5b0-7c3e-7a51-9b2d-4e8f1a6c3d21"` |
| `idempotency-key` | header | string | no | A unique value (a UUID works) that makes a retry safe: sending the same key again returns the first result instead of acting twice. 1–255 printable characters. Example: `"7f3c9a2e-5b1d-4c8e-9f0a-2d6b8e4c1a37"` |
| `content` | body | object | yes | What to send: `{ "type": "text", "text" }`, `{ "type": "media", "media": [{ "url" }], "caption" }`. Templates (`{ "type": "template" }`) are not available yet: refused with `422 operation_not_supported`. |
| `split` | body | "auto" \| "refuse" | no | `auto` (the default) sends a long text as several messages; `refuse` answers `422 content_too_long` instead. |
| `metadata` | body | object | no | Your own key/value pairs, up to 4 KB of JSON, repeated in the message's events. |

## Request

cURL:

```bash
curl -X POST "https://api.vlayers.ai/v1/conversations/$CONVERSATION_ID/messages" \
  -H "Authorization: Bearer $VOICELAYER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "content": {
      "type": "text",
      "text": "Yes, we have a table at 7pm. Shall I book it?"
    }
  }'
```

TypeScript:

```ts
import { createVoiceLayerClient, replyToConversation } from '@voicelayer/api';

const client = createVoiceLayerClient({ apiKey: process.env.VOICELAYER_API_KEY!, throwOnError: true });

const { data } = await replyToConversation({
  client,
  path: {
    id: process.env.CONVERSATION_ID!
  },
  body: {
    content: {
      type: 'text',
      text: 'Yes, we have a table at 7pm. Shall I book it?'
    }
  }
});
console.log(data.message.id);
```

Python:

```python
import os
import voicelayer

config = voicelayer.Configuration(access_token=os.environ["VOICELAYER_API_KEY"])
with voicelayer.ApiClient(config) as client:
    api = voicelayer.ConversationsApi(client)
    result = api.reply_to_conversation(
        id=os.environ["CONVERSATION_ID"],
        reply_to_conversation_request=voicelayer.ReplyToConversationRequest.from_dict({
            "content": {
                "type": "text",
                "text": "Yes, we have a table at 7pm. Shall I book it?",
            },
        }),
    )
    print(result.message.id)
```

## Response `202`

```json
{
  "message": {
    "id": "0192f5b0-8d1f-7b62-8c3e-5f9a2b7d4e32",
    "conversationId": "0192f5b0-7c3e-7a51-9b2d-4e8f1a6c3d21",
    "channel": "sms",
    "direction": "outbound",
    "status": "queued",
    "text": "Yes, we have a table at 7pm. Shall I book it?",
    "media": [],
    "from": "+14155550100",
    "to": "+15550123",
    "bindingId": null,
    "metadata": {},
    "error": null,
    "createdAt": "2026-10-20T15:04:05.000Z",
    "parts": [
      {
        "id": "0192f5b0-8d1f-7b62-8c3e-5f9a2b7d4e32",
        "status": "queued"
      }
    ]
  }
}
```