Hi Vapi Support Team, I’ve hit a major roadblock trying to get my assistant to perform pauses during calls. I’ve tried every method I can find, but nothing seems to work. I want to confirm whether this is a limitation of the platform or if I am missing something. Here’s what I’ve done: 1. SSML tags I inserted tags in my System Prompt in the Assistant tab. I also sent the entire System Prompt with tags via n8n HTTP Request JSON payload to the assistant. Result: Ignores 2. Enabled enableSsmlParsing: true via PATCH request I explicitly set enableSsmlParsing: true through Vapi’s API for the assistant. Result: Ignores 3. tags and chunkPlan I enabled chunkPlan: true via a PATCH request to Vapi’s API. Added tags in the System Prompt and sent them via n8n JSON. Result: No effect 4. Multiple assistant messages / system message instructions I tried splitting lines into multiple assistant messages in the System Prompt. I tried inserting system messages instructing the assistant to “pause” or “wait”. Result: No effect 5. Punctuation / natural speech cues I attempted periods, commas, ellipses, dashes, etc., to induce pauses naturally. Result: Ignored. 6. Testing with ElevenLabs built-in voices Enabled ElevenLabs as the voice provider and selected built-in voices. Tested both Eleven Multilingual v2 and Eleven Turbo v2.5. Result: No effect 7. I understand this is internal and cannot be inserted with a duration. I tried using it in multiple places in the System Prompt. Result: No effect. Questions: Is it currently possible to make an assistant pause during speech using only the System Prompt or via n8n API calls? If yes, what is the exact supported syntax for introducing a pause with ElevenLabs voices (built-in or manual) so I can implement it correctly? If no, can you confirm that this is a platform limitation, and the only way to achieve pauses is via internal Vapi actions or future updates?

Currently, it is not possible to introduce timed pauses (like SSML

<break>

tags) in assistant speech using only the System Prompt or n8n API calls with ElevenLabs voices. The only supported timing control is the VAPI-specific

<flush />

tag, which does not create a pause but simply splits audio at natural boundaries. This is a platform limitation; custom pauses or silences are not available at this time. See the [flush syntax documentation](https://docs.vapi.ai/assistants/flush-syntax) for details. Source: - [Flush syntax documentation](https://docs.vapi.ai/assistants/flush-syntax)

@Vapi Support Bot I got an email from the support team saying the following: "For adding natural pauses, instead of using ellipsis, you’ll want to use SSML tags. This feature is supported primarily with ElevenLabs voices, so make sure your assistant has: enableSsmlParsing: true"..... So if they are telling me that I can use SSML tags, why are you saying that it is not possible to introduce times pauses via SSML <break? tags??

Based on the official documentation, the only supported way to control timing or create pauses in Vapi assistant speech is with the

<flush />

tag—not SSML

<break>

tags—even when using ElevenLabs voices. For example:

"I'm processing your request... <flush /> Let me check that for you."

If you need precise pauses, SSML

<break>

tags are not officially documented as supported. For more, see the [flush syntax documentation](https://docs.vapi.ai/assistants/flush-syntax). Source: - [Flush syntax documentation](https://docs.vapi.ai/assistants/flush-syntax)

@Vapi Support Bot please give me the exact JSON payload I need to use to configure my assistant so it understands tags

To enable your assistant to process

<flush />

tags, add the following to your assistant's configuration:

json
{
  "voice": {
    "chunkPlan": {
      "enabled": true
    }
  }
}

This is the required payload for flush tag support. Without

"chunkPlan.enabled": true

, flush tags will not be recognized. See the [flush syntax documentation](https://docs.vapi.ai/assistants/flush-syntax) for more details. Source: - [Flush syntax documentation](https://docs.vapi.ai/assistants/flush-syntax)

@Vapi Support Bot When I send the PATCH request to modify my assistant's configuration to enable "chunkPlan", I get the following error: { "message": [ "voice.provider must be one of the following values: vapi, 11labs, azure, cartesia, custom-voice, deepgram, hume, lmnt, neuphonic, openai, playht, rime-ai, smallest-ai, tavus, sesame, inworld, minimax, orpheus" ], "error": "Bad Request", "statusCode": 400 } What's the solution? What's the full JSON payload that I should sending via a PATCH request?

To resolve the error, your PATCH payload must include the

"voice.provider"

field along with

"chunkPlan.enabled": true

. Here’s an example JSON payload for ElevenLabs:

json
{
  "voice": {
    "provider": "11labs",
    "chunkPlan": {
      "enabled": true
    }
  }
}

Replace

"11labs"

with your actual provider if different. This structure will enable

<flush />

tag support and satisfy the required fields. See the API reference for more details. Source: - [API reference: calls/create](https://docs.vapi.ai/api-reference/calls/create?explorer=true)

@Vapi Support Bot I am still getting a 400 Bad Request error: { "message": [ "voice.voiceId must be a string" ], "error": "Bad Request", "statusCode": 400 } What am I missing in the JSON payload??

To resolve the

"voice.voiceId must be a string"

error, your PATCH payload must include the

provider

,

voiceId

, and

chunkPlan

fields. Here’s the correct JSON structure (replace

"YOUR_VOICE_ID"

with your actual ElevenLabs voice ID):

json
{
  "voice": {
    "provider": "11labs",
    "voiceId": "YOUR_VOICE_ID",
    "chunkPlan": {
      "enabled": true
    }
  }
}

This will enable

<flush />

tag support and satisfy all required fields according to the [API reference documentation](https://docs.vapi.ai/api-reference/assistants/update). Source: - [API reference: assistants/update](https://docs.vapi.ai/api-reference/assistants/update)