Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Import ElevenLabs conversational AI agents into Telnyx. Preserves instructions, voice settings, tools, and call analysis. Supports all SDK languages.
.claude/skills/team-telnyx-telnyx-import-elevenlabs/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 12% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 39% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 56% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 43% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 85% | 0% |
Migrate your ElevenLabs conversational AI agents to Telnyx in minutes. The import API pulls agent configurations directly from ElevenLabs using your API key and recreates them as Telnyx AI Assistants.
Interaction model: Collect the user's Telnyx API key and ElevenLabs API key, store the ElevenLabs key as a Telnyx integration secret, run the import, then verify. Do NOT skip the secret-creation step — the import endpoint requires a secret reference, not a raw key.
| Component | Imported? | Notes | |-----------|-----------|-------| | Instructions | Yes | Imported as-is | | Greeting / first message | Yes | Maps to assistant greeting | | Voice configuration | Yes | ElevenLabs voice ID and settings preserved | | Dynamic variables | Yes | Default values carried over | | Tools (hangup, transfer, webhook) | Yes | Tool definitions and configurations | | MCP Server integrations | Yes | Server URLs and tool mappings | | Call analysis / insights | Yes | Mapped to insight_settings | | Data retention preferences | Yes | Mapped to privacy_settings | | Knowledge base | No | Must be manually added post-import | | Secrets (API keys in tools) | Partial | Placeholder secrets created — you must re-enter values in the Telnyx portal |
Before importing, store your ElevenLabs API key as an integration secret in Telnyx. Note the secret reference name (e.g., elevenlabs_api_key) — you'll use it in the import call.
You can create integration secrets via the Telnyx Portal under Integration Secrets, or via the API.
Import every conversational AI agent from your ElevenLabs account:
bashcurl \ -X POST \ -H "Authorization: Bearer $TELNYX_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "provider": "elevenlabs", "api_key_ref": "elevenlabs_api_key" }' \ "https://api.telnyx.com/v2/ai/assistants/import"
pythonimport os from telnyx import Telnyx client = Telnyx(api_key=os.environ.get("TELNYX_API_KEY")) assistants = client.ai.assistants.imports( provider="elevenlabs", api_key_ref="elevenlabs_api_key", ) for assistant in assistants.data: print(f"Imported: {assistant.name} (ID: {assistant.id})")
javascriptimport Telnyx from 'telnyx'; const client = new Telnyx(); const assistants = await client.ai.assistants.imports({ provider: 'elevenlabs', api_key_ref: 'elevenlabs_api_key', }); for (const assistant of assistants.data) { console.log(`Imported: ${assistant.name} (ID: ${assistant.id})`); }
goassistants, err := client.AI.Assistants.Imports(context.TODO(), telnyx.AIAssistantImportsParams{ Provider: telnyx.AIAssistantImportsParamsProviderElevenlabs, APIKeyRef: "elevenlabs_api_key", }) if err != nil { panic(err.Error()) } for _, a := range assistants.Data { fmt.Printf("Imported: %s (ID: %s)\n", a.Name, a.ID) }
javaimport com.telnyx.sdk.models.ai.assistants.AssistantImportsParams; import com.telnyx.sdk.models.ai.assistants.AssistantsList; AssistantImportsParams params = AssistantImportsParams.builder() .provider(AssistantImportsParams.Provider.ELEVENLABS) .apiKeyRef("elevenlabs_api_key") .build(); AssistantsList assistants = client.ai().assistants().imports(params); assistants.getData().forEach(a -> System.out.printf("Imported: %s (ID: %s)%n", a.getName(), a.getId()));
rubyassistants = client.ai.assistants.imports( provider: :elevenlabs, api_key_ref: "elevenlabs_api_key" ) assistants.data.each do |a| puts "Imported: #{a.name} (ID: #{a.id})" end
To import only certain agents, pass their ElevenLabs agent IDs in import_ids:
bashcurl \ -X POST \ -H "Authorization: Bearer $TELNYX_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "provider": "elevenlabs", "api_key_ref": "elevenlabs_api_key", "import_ids": ["elevenlabs-agent-id-1", "elevenlabs-agent-id-2"] }' \ "https://api.telnyx.com/v2/ai/assistants/import"
pythonassistants = client.ai.assistants.imports( provider="elevenlabs", api_key_ref="elevenlabs_api_key", import_ids=["elevenlabs-agent-id-1", "elevenlabs-agent-id-2"], )
javascriptconst assistants = await client.ai.assistants.imports({ provider: 'elevenlabs', api_key_ref: 'elevenlabs_api_key', import_ids: ['elevenlabs-agent-id-1', 'elevenlabs-agent-id-2'], });
List your Telnyx assistants to confirm the import succeeded:
bashcurl -H "Authorization: Bearer $TELNYX_API_KEY" \ "https://api.telnyx.com/v2/ai/assistants"
pythonassistants = client.ai.assistants.list() for a in assistants.data: print(f"{a.name} — {a.id} — imported: {a.import_metadata}")
javascriptconst assistants = await client.ai.assistants.list(); for (const a of assistants.data) { console.log(`${a.name} — ${a.id} — imported:`, a.import_metadata); }
After importing, complete these manual steps:
Running the import again for the same ElevenLabs agents will overwrite the existing Telnyx copies with the latest configuration from ElevenLabs. This is useful for syncing changes during a gradual migration.
| Field | Type | Required | Description | |-------|------|----------|-------------| | provider | string | Yes | Must be "elevenlabs" | | api_key_ref | string | Yes | Name of the Telnyx integration secret containing your ElevenLabs API key | | import_ids | arraystring] | No | Specific ElevenLabs agent IDs to import. Omit to import all. |
Endpoint: POST https://api.telnyx.com/v2/ai/assistants/import
Full API docs: https://developers.telnyx.com/api-reference/assistants/import-assistants-from-external-provider
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 17,304 | 10,098 | -42% | 1 | 1 | 0% | 3,494 | 3,929 | +12% | 0 | 0 | — |
case-02 | fail→pass | 15,766 | 9,064 | -43% | 1 | 1 | 0% | 2,724 | 3,777 | +39% | 0 | 0 | — |
case-03 | fail→pass | 12,363 | 7,998 | -35% | 1 | 1 | 0% | 2,267 | 3,532 | +56% | 0 | 0 | — |
case-04 | fail→pass | 13,077 | 7,761 | -41% | 1 | 1 | 0% | 2,392 | 3,421 | +43% | 0 | 0 | — |
case-05 | pass→pass | 8,645 | 5,223 | -40% | 1 | 1 | 0% | 1,707 | 3,213 | +88% | 0 | 0 | — |
case-06 | pass→pass | 11,818 | 11,537 | -2% | 1 | 1 | 0% | 2,193 | 4,284 | +95% | 0 | 0 | — |
case-07 | fail→pass | 10,403 | 6,897 | -34% | 1 | 1 | 0% | 1,858 | 3,438 | +85% | 0 | 0 | — |
case-08 | fail→pass | 10,198 | 5,569 | -45% | 1 | 1 | 0% | 1,820 | 3,253 | +79% | 0 | 0 | — |
case-09 | fail→pass | 11,258 | 4,181 | -63% | 1 | 1 | 0% | 2,221 | 2,747 | +24% | 0 | 0 | — |
case-10 | fail→pass | 11,399 | 6,162 | -46% | 1 | 1 | 0% | 1,904 | 3,001 | +58% | 0 | 0 | — |
case-11 | fail→pass | 7,860 | 7,159 | -9% | 1 | 1 | 0% | 1,234 | 2,485 | +101% | 0 | 0 | — |
case-12 | pass→pass | 7,946 | 3,659 | -54% | 1 | 1 | 0% | 1,201 | 2,586 | +115% | 0 | 0 | — |
case-13 | pass→pass | 8,849 | 6,803 | -23% | 1 | 1 | 0% | 1,427 | 3,250 | +128% | 0 | 0 | — |
case-14 | fail→pass | 8,305 | 2,790 | -66% | 1 | 1 | 0% | 1,416 | 2,511 | +77% | 0 | 0 | — |
case-15 | fail→pass | 11,242 | 5,245 | -53% | 1 | 1 | 0% | 1,960 | 3,097 | +58% | 0 | 0 | — |
case-16 | pass→pass | 12,630 | 2,517 | -80% | 1 | 1 | 0% | 1,965 | 2,355 | +20% | 0 | 0 | — |
case-17 | fail→pass | 9,773 | 2,036 | -79% | 1 | 1 | 0% | 1,595 | 2,252 | +41% | 0 | 0 | — |
case-18 | pass→pass | 6,614 | 2,063 | -69% | 1 | 1 | 0% | 1,117 | 2,355 | +111% | 0 | 0 | — |
case-19 | fail→pass | 16,910 | 4,917 | -71% | 1 | 1 | 0% | 2,785 | 2,846 | +2% | 0 | 0 | — |
case-20 | pass→pass | 10,807 | 1,795 | -83% | 1 | 1 | 0% | 1,738 | 2,332 | +34% | 0 | 0 | — |
case-21 | fail→pass | 7,099 | 2,516 | -65% | 1 | 1 | 0% | 1,059 | 2,507 | +137% | 0 | 0 | — |
case-22 | fail→pass | 11,793 | 3,193 | -73% | 1 | 1 | 0% | 1,759 | 2,571 | +46% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of +68 percentage points is the difference between those two pass rates over the 22 comparable cases.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.