Add memory

Enable memory on the agent

Toggle memory in the console, or PATCH the agent:

1
curl -X PATCH https://api.speechify.ai/v1/agents/id \
2
     -H "Authorization: Bearer <token>" \
3
     -H "Content-Type: application/json" \
4
     -d '{}'

memory_retention_days caps retrieval and the nightly cleanup; 0 means no cap.

Reference the placeholder in the prompt

Add {{memory}} where you want the facts grounded. The retrieved block is already a numbered list, so keep the surrounding prompt short.

You are a support agent for Acme. Speak concisely.
{{memory}}
Greet the caller, confirm what they need, and escalate only if you can't resolve it in one turn.

With memory disabled, the placeholder is stripped — no literal braces reach the LLM.

Pass a stable caller identity

Memory pivots on caller_identity, taken from the LiveKit participant identity:

• Console test calls and authenticated SDK starts → user_<firebase-uid>, set for you.
• Public widget → pass user_identity yourself (a stable ID such as a hashed email).

1
<speechify-agent
2
  agent-id="agent_01H..."
3
  user-identity="acme_user_42">
4
</speechify-agent>

The widget’s user-identity attribute becomes the caller_identity on every memory — see Embed. Anonymous sessions — no user-identity — skip memory.

Verify it end to end

1. Give the agent a prompt containing {{memory}} and enable memory.
2. Place a test call and state something durable — “I can only do mornings; I’m vegetarian.” Hang up.
3. On the conversation detail page, Memories written this call lists the facts within about ten seconds.
4. Call again as the same caller and ask an open question — the agent should use the fact without re-asking.