{
  "data": null,
  "kind": "anchor.page",
  "links": {
    "api": "https://www.anchorterminal.com/api/v1/index.json",
    "html": "https://www.anchorterminal.com/niches/voice-agents.tool-call-mid-call/",
    "json": "https://www.anchorterminal.com/niches/voice-agents.tool-call-mid-call/index.json",
    "llms": "https://www.anchorterminal.com/llms.txt",
    "markdown": "https://www.anchorterminal.com/niches/voice-agents.tool-call-mid-call/index.md",
    "mcp": "https://www.anchorterminal.com/mcp",
    "slim": "https://www.anchorterminal.com/niches/voice-agents.tool-call-mid-call/index.min.md"
  },
  "markdown": "Two or three companies' docs show a full fit.\n\n| Companies, full fit | With a limit | Carry the tag | Share of the category's work | First-hand accounts |\n| --- | --- | --- | --- | --- |\n| 2 | 17 | 30 | 18 | 9 |\n\n## What counts as done\n\nPrecisely one execution per intended action, a spoken confirmation that matches the tool's real result, and the conversation resumes without a client nudge in one response cycle.\n\nMeasured, for our own tests: no more than 4 seconds of silence before a filler or result.\n\nHow agents ask for it: book the slot while the caller is on the line; look up the order and read it back; issue the refund and confirm it\n\n## Does the job\n\nThe docs show it meets the test above, and nothing we read says otherwise.\n\n- **GPT-Live (OpenAI OpCo, LLC)**: Backend work keeps running while GPT-Live talks; an automatic acknowledgement covers the wait (acknowledgement_delay_ms), and session.commentary.append speaks the verified result without a new response request. Appended instructions do not cancel backend work.\n- **Ultravox Realtime API (Theai, Inc. dba Inworld AI)**: Non-precomputable tools are invoked only after the agent's utterance ends and the conversation is frozen while they run, so barge-in does not cancel a write; the agent speaks after the result by default (agent reaction), timeout 2.5 s default, 40 s max.\n\n## Does the job, with a limit\n\nIt does the job, but something in the docs or a user's account will get in an agent's way. The limit is named in each row.\n\n- **Amazon Nova 2 Sonic (Amazon Web Services, Inc.)**: Tools run asynchronously and are not cancelled by new speech; toolChoice can force a tool. No cancellation event, results are always delivered so the model may issue a second call, and a LiveKit account saw results held until the user spoke (fixed).\n- **AssemblyAI Voice Agent API (AssemblyAI, Inc.)**: Per-tool execution_mode: interactive speaks a filler while the tool runs, hold mutes replies; tool.result auto-fires the next reply. What happens to an in-flight tool on barge-in, any cancellation event, and tool forcing are not documented.\n- **Bland AI API + MCP (Intelliga Corporation)**: Agent speech fills the wait and a 1 to 30 second cooldown limits repeat calls, but nothing documents whether caller speech cancels a running tool or whether a cancelled tool is re-issued.\n- **Bolna API + MCP (Voxlabs Private Limited)**: pre_call_message fills the wait while an API tool runs. No tool timeout range, cancellation-on-interruption behaviour or dedupe of re-issued calls is documented.\n- **Deepgram Voice Agent API (Deepgram, Inc.)**: FunctionCallCancelled tells the client which calls were abandoned and late responses are dropped; defer_until_eot stops speculative dispatch. But barge-in still cancels a running call with no per-tool opt-out, and tool timeouts are undocumented.\n- **ElevenLabs Agents API + MCP (Eleven Labs Inc.)**: Per tool: pre_tool_speech auto, force or off; execution_mode immediate, post_tool_speech or async; interruption_mode can block barge-in during the tool; timeouts 5 to 300 s (webhook) or 1 to 120 s (client). Errors are hidden by default and no cancellation event is documented.\n- **Fresha AI Concierge (Fresha.com SV Ltd)**: Books against the Fresha calendar during the call per the vendor, but no developer tools can be registered and nothing documents fillers, timeouts or what the caller hears if a booking fails.\n- **Gemini Live API (Google LLC)**: Per-function BLOCKING or NON_BLOCKING behaviour, INTERRUPT, WHEN_IDLE or SILENT scheduling and a toolCallCancellation message are documented, but a user test found no cancellation and the same booking re-issued under a new id in 7 of 12 runs.\n- **Inworld Realtime API (Theai, Inc. dba Inworld AI)**: auto_tool_response (default true) continues after a function_call_output, responsiveness fillers cover slow tools and tool_choice can force a named function. The docs don't say what happens to a pending call when interrupt_response cancels the response.\n- **LiveKit Agents (LiveKit Incorporated)**: Per-tool disallow_interruptions, hold messages, tool_choice per reply and automatic continuation are documented, but on_duplicate defaults to allow and matches duplicates by tool name only, so precisely-once needs explicit settings.\n- **OpenAI Realtime API (OpenAI OpCo, LLC)**: Function tools run in the client and tool_choice works at session and response level, but after function_call_output the client must send response.create, no cancellation event is documented, and there is no filler setting.\n- **Pipecat (Daily)**: Per-tool cancel_on_interruption, timeout_secs, on_function_calls_started fillers and run_llm continuation exist, but the default cancels on any speech; an open issue shows a refund that landed reported as cancelled and some models refunding twice.\n- **Retell AI API + MCP (Retell AI Inc.)**: Speak During and After Execution, timeout_ms and error results cover fillers and continuation, but Retell's own custom-LLM guide says a response discarded when the caller keeps talking is re-requested, so a tool runs twice unless the developer adds an idempotency key.\n- **Rime Prism (Rime Labs, Inc.)**: prism_filler sets the phrase during a tool and failures are spoken from the result, but the backend must ask Prism to continue after each result, a tool cannot be forced, and Prism does not deduplicate requests.\n- **Synthflow API + MCP (AgentFlow AI GmbH)**: Custom actions have start, delay (threshold 0 to 30 s) and failure messages and a timeout up to 30 s, but the docs read say nothing on cancellation by caller speech, duplicate execution or forcing an action.\n- **Vaani Developer Platform (Vaani AI Research Private Limited (Bengaluru, India, CIN U62099KA2025PTC201212))**: Tools are defined from a cURL request and triggered by a natural-language description, with configurable filler words, but nothing documents timeouts, duplicate execution, interruption or what the agent says on failure.\n- **Vapi API + MCP (Vapi Inc.)**: Filler messages (request-start, request-response-delayed after N ms) and automatic resumption after the result are documented, but no cancellation event, no toolChoice field, and timeouts are not retried while the server may still complete the write.\n- **Vocily AI (VOCILY AI PRIVATE LIMITED)**: Each action has a short message spoken before it runs and a message for failure, but no timeout, cancellation-on-speech or duplicate-execution behaviour is documented in the tools page or the OpenAPI file.\n- **Vogent API (Monoid, Inc.)**: FunctionLifecycleMessages give started and waiting lines, and awaitSpeech holds a function until the agent stops talking. Nothing documents a timeout, what happens when the caller interrupts a running function, or duplicate execution.\n\n## Couldn't check\n\nThe docs were closed to us, or silent. These carry no mark either way.\n\n- **Harmony.ai (monday.com Ltd.)**: No page read documents how the agent runs actions mid-call, fillers, timeouts or cancellation; agent behaviour is set in the web app only.\n- **Hume EVI (Empathic Voice Interface) (Hume AI, Inc.)**: EVI docs withdrawn: every EVI page, including the overview and tool-use guide, redirects to the Audio Decisions overview, and the EVI AsyncAPI file returns 404. The last assessment recorded EVI access ending 13 November 2026.\n\n- not this job: CueLight (sshah03 (individual GitHub account, no name or organisation stated)): No tool calling or conversation; it returns an end-of-turn probability per 20 ms of audio.\n- not this job: fone.me (Fone): A hosted personal agent with no developer-registered tools or webhooks; outside agents reach it only through message_agent and A2A.\n- not this job: Pipecat PhoneLLM (Daily): The card covers tool calling through vLLM's qwen3_coder parser, but cancellation, fillers, timeouts and precisely-once execution belong to the voice framework, not the model.\n- not this job: PlaceCall (VOYGR Tech, Inc.): The developer cannot register tools for the call agent; the only mid-call hook is ask_user, a question routed to the caller's agent.\n\n## What stops agents finishing\n\n- default cancel-on-interruption with no per-tool override\n- no cancellation event when a blocking tool is interrupted, so the model re-issues the call\n- tool result held behind the model's own speech until the caller speaks again\n\n## Around it\n\nBefore: voice-agents.inbound-receptionist. After: booking.reservations, payments.refund, crm.update-record.\n\n## Where this comes from\n\nWeight 18 of 100 in Conversational voice agents: 9 of 31 accounts are tool-call failures in flight (acc-02, acc-03, acc-05, acc-14, acc-16, acc-17, acc-22, acc-24, acc-26); the largest failure cluster found\n\nAs data: https://www.anchorterminal.com/api/v1/use-cases/voice-agents.tool-call-mid-call.json, or the MCP tool get_use_case with id voice-agents.tool-call-mid-call. Draft, read 2026-11-12 from public docs and first-hand accounts, not yet reviewed by a person.\n",
  "meta": {
    "attribution": "Anchor Terminal (https://www.anchorterminal.com)",
    "attributionRequired": true,
    "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)",
    "docs": "https://www.anchorterminal.com/docs/",
    "generatedAt": "2026-11-16",
    "license": "CC-BY-4.0",
    "method": "https://www.anchorterminal.com/benchmark/",
    "methodology": "0.8",
    "openapi": "https://www.anchorterminal.com/openapi.json",
    "preview": false,
    "run": "2026-10-01",
    "runLabel": "October 2026 research run",
    "terms": "https://www.anchorterminal.com/terms/#data"
  },
  "page": {
    "breadcrumbs": [
      {
        "name": "Home",
        "url": "https://www.anchorterminal.com/"
      },
      {
        "name": "For agents",
        "url": "https://www.anchorterminal.com/agents/"
      },
      {
        "name": "Niches",
        "url": "https://www.anchorterminal.com/niches/"
      },
      {
        "name": "Run a tool during a live call and tell the caller the true outcome",
        "url": ""
      }
    ],
    "description": "Run a tool during a live call and tell the caller the true outcome: 2 companies fully do it, 17 with a limit, 30 carry the tag. Every listing in Conversational voice agents with the reason and a source.",
    "facts": null,
    "h1": "Run a tool during a live call and tell the caller the true outcome",
    "image": "https://www.anchorterminal.com/assets/og/default.png",
    "path": "/niches/voice-agents.tool-call-mid-call/",
    "published": "",
    "section": "agents",
    "title": "Run a tool during a live call and tell the caller the true outcome |…",
    "toc": null,
    "updated": "2026-11-15",
    "url": "https://www.anchorterminal.com/niches/voice-agents.tool-call-mid-call/"
  },
  "tokens": {
    "markdown": 2400,
    "slim": 430
  },
  "version": 1
}
