apunkt/dograh
1
0
Fork 0
mirror of https://github.com/dograh-hq/dograh.git synced 2026-06-07 07:55:16 +02:00
Code Issues Projects Releases Packages Wiki Activity

feat: add recording audio option in tool and node transitions (#232)

Browse source 
* feat: allow uploading recording as part of node transition

* feat: allow recordings in tool transitions

* chore: fix tests
This commit is contained in:
Abhishek 2026-04-10 17:53:42 +05:30 • committed by GitHub
parent 3f19a16e7f
commit 7c245051d2
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
54 changed files with 3575 additions and 640 deletions
Download patch file Download diff file Expand all files Collapse all files

26
docs/voice-agent/pre-recorded-audio.mdx
View file

@ -6,15 +6,6 @@ tag: "NEW"
Custom recordings allow you to build **hybrid voice agents** that use your own pre-recorded audio for key parts of the conversation, while falling back to LLM-generated speech (via a cloned voice) for dynamic responses. This gives you the best of both worlds — the emotional depth of real human speech and the flexibility of AI-generated dialogue.
<iframe
className="w-full aspect-video rounded-xl"
src="https://www.youtube.com/embed/1uZqhG0_cIo"
title="Dograh Twilio Setup"
allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture"
allowFullScreen
></iframe>
## Why use custom recordings?
- **Reduced TTS cost** — Pre-recorded audio is played directly, so you are not charged for TTS synthesis on those segments.
@ -50,23 +41,20 @@ You can use any TTS provider that supports voice cloning. The steps will vary by
## Step 3: Upload recordings
Navigate to your agent in the workflow builder and open the **Recordings** panel. You can either upload pre-recorded audio files or record directly in the browser.
Navigate to the **Recordings** page in the Dograh dashboard. Recordings are shared across all agents in your organization. You can either upload pre-recorded audio files or record directly in the browser.
For each recording:
1. Click **Record** (or upload a file).
2. Speak the exact phrase you want the agent to use.
3. Give the recording a descriptive name (e.g., `greeting`, `invitation`, `venue`).
4. Verify the transcription is correct — edit it if needed.
5. Click **Upload**.
1. Click **Upload Recording**.
2. Choose an audio file or click **Record** to record in the browser.
3. Verify the transcription is correct — edit it if needed.
4. Click **Upload**.
<Warning>
Recordings are scoped to a specific **provider and Voice ID**. If you change either, you will need to re-upload your recordings to ensure consistency between the recorded audio and the cloned voice used for dynamic responses.
</Warning>
You can rename a recording's ID at any time by clicking the edit icon next to it in the recordings list.
## Step 4: Build the workflow
Open your agent's workflow and write the conversation flow in natural language. To insert a recording, type **`@`** in the prompt editor — this will show a list of all available recordings scoped to your current Voice ID.
Open your agent's workflow and write the conversation flow in natural language. To insert a recording, type **`@`** in the prompt editor — this will show a list of all available recordings in your organization.
For any user question that falls outside your recordings, the agent automatically generates a dynamic response using the LLM, which is then synthesized using your cloned voice via TTS.