{
  "listings": [
    {
      "slug": "gpt-live",
      "name": "GPT-Live",
      "company": "OpenAI OpCo, LLC",
      "grade": "BB",
      "fit": "yes",
      "why": "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.",
      "source": "https://developers.openai.com/api/docs/guides/live-delegation.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/gpt-live"
    },
    {
      "slug": "ultravox",
      "name": "Ultravox Realtime API",
      "company": "Theai, Inc. dba Inworld AI",
      "grade": "C",
      "fit": "yes",
      "why": "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.",
      "source": "https://docs.ultravox.ai/tools/async-tools.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/ultravox"
    },
    {
      "slug": "amazon-nova-sonic",
      "name": "Amazon Nova 2 Sonic",
      "company": "Amazon Web Services, Inc.",
      "grade": "B",
      "fit": "caveat",
      "why": "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).",
      "source": "https://docs.aws.amazon.com/nova/latest/nova2-userguide/sonic-async-tools.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/amazon-nova-sonic"
    },
    {
      "slug": "assemblyai-voice-agent",
      "name": "AssemblyAI Voice Agent API",
      "company": "AssemblyAI, Inc.",
      "grade": "C",
      "fit": "caveat",
      "why": "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.",
      "source": "https://www.assemblyai.com/docs/voice-agents/voice-agent-api/tools/overview.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/assemblyai-voice-agent"
    },
    {
      "slug": "bland-ai",
      "name": "Bland AI API + MCP",
      "company": "Intelliga Corporation",
      "grade": "B",
      "fit": "caveat",
      "why": "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.",
      "source": "https://docs.bland.ai/tutorials/tools/custom-api.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/bland-ai"
    },
    {
      "slug": "bolna",
      "name": "Bolna API + MCP",
      "company": "Voxlabs Private Limited",
      "grade": "D",
      "fit": "caveat",
      "why": "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.",
      "source": "https://www.bolna.ai/docs/tool-calling/custom-function-schema",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/bolna"
    },
    {
      "slug": "deepgram-voice-agent",
      "name": "Deepgram Voice Agent API",
      "company": "Deepgram, Inc.",
      "grade": "BB",
      "fit": "caveat",
      "why": "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.",
      "source": "https://developers.deepgram.com/docs/voice-agent-function-call-cancelled.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/deepgram-voice-agent"
    },
    {
      "slug": "elevenlabs-agents",
      "name": "ElevenLabs Agents API + MCP",
      "company": "Eleven Labs Inc.",
      "grade": "BB",
      "fit": "caveat",
      "why": "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.",
      "source": "https://elevenlabs.io/docs/eleven-agents/api-reference/tools/create.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/elevenlabs-agents"
    },
    {
      "slug": "fresha-ai-concierge",
      "name": "Fresha AI Concierge",
      "company": "Fresha.com SV Ltd",
      "grade": "F",
      "fit": "caveat",
      "why": "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.",
      "source": "https://www.fresha.com/for-business/features/ai-concierge",
      "confidence": "low",
      "url": "https://www.anchorterminal.com/tools/fresha-ai-concierge"
    },
    {
      "slug": "gemini-live",
      "name": "Gemini Live API",
      "company": "Google LLC",
      "grade": "C",
      "fit": "caveat",
      "why": "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.",
      "source": "https://aistudio.google.com/docs/live-api/tools.md",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/gemini-live"
    },
    {
      "slug": "inworld-realtime",
      "name": "Inworld Realtime API",
      "company": "Theai, Inc. dba Inworld AI",
      "grade": "B",
      "fit": "caveat",
      "why": "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.",
      "source": "https://docs.inworld.ai/realtime/usage/tool-calling.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/inworld-realtime"
    },
    {
      "slug": "livekit-agents",
      "name": "LiveKit Agents",
      "company": "LiveKit Incorporated",
      "grade": "BB",
      "fit": "caveat",
      "why": "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.",
      "source": "https://docs.livekit.io/llms-full.txt",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/livekit-agents"
    },
    {
      "slug": "openai-realtime",
      "name": "OpenAI Realtime API",
      "company": "OpenAI OpCo, LLC",
      "grade": "BB",
      "fit": "caveat",
      "why": "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.",
      "source": "https://developers.openai.com/api/docs/guides/realtime-mcp.md",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/openai-realtime"
    },
    {
      "slug": "pipecat",
      "name": "Pipecat",
      "company": "Daily",
      "grade": "B",
      "fit": "caveat",
      "why": "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.",
      "source": "https://docs.pipecat.ai/pipecat/learn/function-calling.md",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/pipecat"
    },
    {
      "slug": "retell-ai",
      "name": "Retell AI API + MCP",
      "company": "Retell AI Inc.",
      "grade": "B",
      "fit": "caveat",
      "why": "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.",
      "source": "https://docs.retellai.com/llms-full.txt",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/retell-ai"
    },
    {
      "slug": "rime-prism",
      "name": "Rime Prism",
      "company": "Rime Labs, Inc.",
      "grade": "B",
      "fit": "caveat",
      "why": "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.",
      "source": "https://docs.rime.ai/docs/prism/tools.md",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/rime-prism"
    },
    {
      "slug": "synthflow",
      "name": "Synthflow API + MCP",
      "company": "AgentFlow AI GmbH",
      "grade": "D",
      "fit": "caveat",
      "why": "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.",
      "source": "https://docs.synthflow.ai/about-custom-actions.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/synthflow"
    },
    {
      "slug": "vaani-voice",
      "name": "Vaani Developer Platform",
      "company": "Vaani AI Research Private Limited (Bengaluru, India, CIN U62099KA2025PTC201212)",
      "grade": "E",
      "fit": "caveat",
      "why": "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.",
      "source": "https://docs.vaanivoice.ai/getting-started/agent-config/training",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/vaani-voice"
    },
    {
      "slug": "vapi",
      "name": "Vapi API + MCP",
      "company": "Vapi Inc.",
      "grade": "B",
      "fit": "caveat",
      "why": "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.",
      "source": "https://docs.vapi.ai/tools/api-request/reliability.md",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/vapi"
    },
    {
      "slug": "vocily",
      "name": "Vocily AI",
      "company": "VOCILY AI PRIVATE LIMITED",
      "grade": "C",
      "fit": "caveat",
      "why": "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.",
      "source": "https://docs.vocily.ai/building-agents/tools.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/vocily"
    },
    {
      "slug": "vogent",
      "name": "Vogent API",
      "company": "Monoid, Inc.",
      "grade": "E",
      "fit": "caveat",
      "why": "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.",
      "source": "https://docs.vogent.ai/api-reference/openapi.yaml",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/vogent"
    },
    {
      "slug": "harmony-ai",
      "name": "Harmony.ai",
      "company": "monday.com Ltd.",
      "grade": "E",
      "fit": "unchecked",
      "why": "No page read documents how the agent runs actions mid-call, fillers, timeouts or cancellation; agent behaviour is set in the web app only.",
      "source": "https://docs.harmony.ai/llms-full.txt",
      "confidence": "low",
      "url": "https://www.anchorterminal.com/tools/harmony-ai"
    },
    {
      "slug": "hume-evi",
      "name": "Hume EVI (Empathic Voice Interface)",
      "company": "Hume AI, Inc.",
      "grade": "C",
      "fit": "unchecked",
      "why": "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.",
      "source": "https://dev.hume.ai/docs/speech-to-speech-evi/overview",
      "confidence": "low",
      "url": "https://www.anchorterminal.com/tools/hume-evi"
    },
    {
      "slug": "cuelight",
      "name": "CueLight",
      "company": "sshah03 (individual GitHub account, no name or organisation stated)",
      "grade": "D",
      "fit": "no",
      "why": "No tool calling or conversation; it returns an end-of-turn probability per 20 ms of audio.",
      "source": "https://raw.githubusercontent.com/sshah03/CueLight/main/README.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/cuelight"
    },
    {
      "slug": "fone-me",
      "name": "fone.me",
      "company": "Fone",
      "grade": "F",
      "fit": "no",
      "why": "A hosted personal agent with no developer-registered tools or webhooks; outside agents reach it only through message_agent and A2A.",
      "source": "https://www.fone.me/llms.txt",
      "confidence": "low",
      "url": "https://www.anchorterminal.com/tools/fone-me"
    },
    {
      "slug": "pipecat-phonellm",
      "name": "Pipecat PhoneLLM",
      "company": "Daily",
      "grade": "B",
      "fit": "no",
      "why": "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.",
      "source": "https://huggingface.co/pipecat-ai/phonellm-mini-alpha-2",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/pipecat-phonellm"
    },
    {
      "slug": "placecall",
      "name": "PlaceCall",
      "company": "VOYGR Tech, Inc.",
      "grade": "C",
      "fit": "no",
      "why": "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.",
      "source": "https://github.com/voygr-tech/placecall/blob/main/AGENTS.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/placecall"
    }
  ],
  "marks": "yes: the docs show it does the job as the success test says. caveat: it does the job with a limit an agent should know. no: it doesn't do this job. unchecked: we couldn't read it.",
  "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"
  },
  "useCase": {
    "accounts": 9,
    "after": [
      "booking.reservations",
      "payments.refund",
      "crm.update-record"
    ],
    "area": "voice",
    "asks": [
      "book the slot while the caller is on the line",
      "look up the order and read it back",
      "issue the refund and confirm it"
    ],
    "before": [
      "voice-agents.inbound-receptionist"
    ],
    "blockers": [
      "default cancel-on-interruption with no per-tool override",
      "no cancellation event when a blocking tool is interrupted, so the model re-issues the call",
      "tool result held behind the model's own speech until the caller speaks again"
    ],
    "capabilities": [
      "voice.agent",
      "voice.tools",
      "voice.speech-to-speech",
      "voice.pipeline"
    ],
    "category": "voice-agents",
    "categoryName": "Conversational voice agents",
    "checked": "2026-11-12",
    "companies": {
      "fit": 2,
      "fitWithLimit": 17,
      "tagged": 30
    },
    "competition": "few",
    "fits": [
      "gpt-live",
      "ultravox"
    ],
    "fitsWithLimit": [
      "amazon-nova-sonic",
      "assemblyai-voice-agent",
      "bland-ai",
      "bolna",
      "deepgram-voice-agent",
      "elevenlabs-agents",
      "fresha-ai-concierge",
      "gemini-live",
      "inworld-realtime",
      "livekit-agents",
      "openai-realtime",
      "pipecat",
      "retell-ai",
      "rime-prism",
      "synthflow",
      "vaani-voice",
      "vapi",
      "vocily",
      "vogent"
    ],
    "id": "voice-agents.tool-call-mid-call",
    "listings": {
      "caveat": 19,
      "no": 4,
      "notRead": 0,
      "tagged": 33,
      "unchecked": 2,
      "yes": 2
    },
    "name": "Run a tool during a live call and tell the caller the true outcome",
    "status": "draft",
    "success": "Precisely 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. Measured: no more than 4 seconds of silence before a filler or result.",
    "url": "https://www.anchorterminal.com/api/v1/use-cases/voice-agents.tool-call-mid-call.json",
    "weight": 18,
    "weightBasis": "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"
  }
}
