Is it possible to get a recording of your elevenlabs conversation in a public url? So after a conve | ElevenLabs | Page 1

odd ivyBOT Oct 23, 2025, 11:47 AM

#

AI-generated Answer for yves_69297

Short answer: you can retrieve a call recording after a conversation, but ElevenLabs does not provide a built‑in public URL. You must fetch the audio via the authenticated API or receive it in a post‑call webhook, then host it yourself (e.g., upload to your storage and share a signed link). (elevenlabs.io)

How to do it:

Ensure call audio is being saved for the agent; otherwise no recording will be available. (elevenlabs.io)
From the SDK, capture the conversation_id (e.g., via the SDK connect callback), which you’ll use to fetch the recording. (elevenlabs.io)
Check if audio exists (has_audio/has_user_audio/has_response_audio) via GET /v1/convai/conversations/:conversation_id. (elevenlabs.io)
Retrieve the recording:
- API: GET /v1/convai/conversations/:conversation_id/audio (requires xi-api-key header, so it’s not a public link). (elevenlabs.io)
- Webhook: enable post_call_audio to receive base64 of the full conversation in your endpoint. (elevenlabs.io)
To share with the user, upload the audio to your storage (e.g., S3) and generate a time‑limited URL; see the SDK cookbook for an example of creating and sharing a signed S3 link. (elevenlabs.io)

So: yes, you can give users a recording after the call—but you generate the shareable URL from your own storage; ElevenLabs does not issue a public recording URL. (elevenlabs.io)

opal hollow Oct 24, 2025, 6:42 AM

#

Is it correct that the audio is in the following format?

49 44 33 04 00 00 00 00 00 23 54 53 53 45 00 00 00 0f 00 00 03 4c 61 76 66 36 30 2e 31 36 2e 31 et cetera

odd ivyBOT Oct 24, 2025, 6:42 AM

#

AI-generated Answer for yves_69297

Short answer: treat it as MP3.

ElevenLabs’ post-call audio webhooks deliver the full conversation audio as a base64‑encoded MP3. (elevenlabs.io)
The GET conversation audio endpoint returns the call recording; while the page doesn’t state the codec explicitly, MP3 is the default output format across ElevenLabs audio responses. (elevenlabs.io)
Supported API output formats include MP3 (various sample rates/bitrates), PCM, Opus, μ‑law, and A‑law; however, conversation audio delivered via the audio webhook is documented as MP3. (help.elevenlabs.io)

If you need a different codec for recordings, the docs don’t currently document an alternative for the conversation recording payload itself; only the TTS endpoints expose selectable output_format. (elevenlabs.io)

Sources:
Post-call webhooks | ElevenLabs Documentation
Get conversation audio | ElevenLabs Documentation
What audio formats do you support? – ElevenLabs
Text to Speech | ElevenLabs Documentation

opal hollow Oct 24, 2025, 6:45 AM

#

This is the output bundle:

[
{
"body": "IMTBuffer(789151, binary, 36c3961772f0cebafa6fece8a51a1bdb78774cb0): 49443304000000000023545353450000000f0000034c61766636302e31362e3130300000000000000000000000fffb90c40003c00001a400000020000034800000044c414d45332e31303055555555555555555555555555555555555555555555555555",
"headers": {
"date": "Fri, 24 Oct 2025 06:41:31 GMT",
"server": "uvicorn",
"content-type": "audio/mpeg",
"access-control-allow-origin": "",
"access-control-allow-headers": "",
"access-control-allow-methods": "POST, PATCH, OPTIONS, DELETE, GET, PUT",
"access-control-max-age": "600",
"strict-transport-security": "max-age=31536000; includeSubDomains",
"x-trace-id": "d178b9e2a2b5aba83b0a7e570e285dd5",
"x-region": "us-central1",
"via": "1.1 google, 1.1 google",
"alt-svc": "h3=":443"; ma=2592000,h3-29=":443"; ma=2592000",
"connection": "close",
"transfer-encoding": "chunked"
},
"statusCode": 200
}
]

How can I turn this into a useful recording?

#Is it possible to get a recording of your elevenlabs conversation in a public url? So after a conve