{
  "slug": "voice-agent-cost-per-minute",
  "title": "How to Compute Your Voice Agent Cost per Minute",
  "description": "How to compute a voice agent cost per minute from your own pilot: symbolic formulas for native speech-to-speech and cascaded STT, LLM and TTS, the variables that move the result, idle audio, retries, tool-call turns, and a sensitivity check.",
  "kind": "sub",
  "order": 7,
  "target_query": "voice agent cost per minute",
  "secondary_queries": [
    "ai voice agent pricing per minute",
    "realtime api cost per minute"
  ],
  "tags": [
    "voice",
    "cost",
    "pricing",
    "realtime",
    "cascaded",
    "speech-to-speech",
    "agents",
    "production"
  ],
  "published": "2026-10-10",
  "updated": "2026-10-10",
  "words": 1514,
  "estimated_tokens": 2014,
  "premium": false,
  "rights": {
    "access": "free",
    "note": "Editorial guides are always free and never part of the licensed corpus.",
    "license": "https://changegamer.ai/license.xml",
    "pricing": "https://changegamer.ai/api/pricing.json",
    "payment": "https://changegamer.ai/api/payment.json"
  },
  "license": "https://changegamer.ai/license.xml",
  "citation": "ChangeGamer (2026-10-10). How to Compute Your Voice Agent Cost per Minute. ChangeGamer. https://changegamer.ai/articles/voice-agent-cost-per-minute (updated 2026-10-10).",
  "bibtex": "@misc{changegamer_voice_agent_cost_per_minute, title = {How to Compute Your Voice Agent Cost per Minute}, publisher = {ChangeGamer}, year = {2026}, url = {https://changegamer.ai/articles/voice-agent-cost-per-minute}, note = {Updated 2026-10-10}}",
  "canonical": "https://changegamer.ai/articles/voice-agent-cost-per-minute",
  "markdown": "https://changegamer.ai/articles/voice-agent-cost-per-minute.md",
  "takeaways": [
    "A voice agent cost per minute cannot be looked up, because it depends on tokens per audio minute, turns per call, talk ratio and silence handling, so it has to be computed from usage measured in your own pilot.",
    "The voice-realtime-agents reference lists OpenAI audio prices of roughly $32 and $64 per 1M input and output tokens for the full realtime model and $10 and $20 for the mini, verified 2026-07-09 and not re-verified 2026-09-28.",
    "Audio tokens are priced at roughly 3 to 10 times text-token rates (voice-realtime-agents, verified 2026-07-09), so audio and text token counts must be recorded separately or the cost model will be wrong.",
    "As the author's inference, a cascaded voice agent has three cost terms per turn, speech-to-text, language model and text-to-speech, and each must be priced from that vendor's own dated rate card, which the corpus does not contain.",
    "As the author's inference, the dominant cost drivers to test first are tokens per audio minute, silence billed as input, and conversation history re-sent on every turn, because each multiplies the whole bill rather than one line."
  ],
  "outline": [
    {
      "depth": 2,
      "text": "What can the corpus tell you about voice agent pricing?",
      "anchor": "what-can-the-corpus-tell-you-about-voice-agent-pricing",
      "url": "https://changegamer.ai/articles/voice-agent-cost-per-minute#what-can-the-corpus-tell-you-about-voice-agent-pricing"
    },
    {
      "depth": 2,
      "text": "What is the formula for a native speech-to-speech agent?",
      "anchor": "what-is-the-formula-for-a-native-speech-to-speech-agent",
      "url": "https://changegamer.ai/articles/voice-agent-cost-per-minute#what-is-the-formula-for-a-native-speech-to-speech-agent"
    },
    {
      "depth": 2,
      "text": "What is the formula for a cascaded agent?",
      "anchor": "what-is-the-formula-for-a-cascaded-agent",
      "url": "https://changegamer.ai/articles/voice-agent-cost-per-minute#what-is-the-formula-for-a-cascaded-agent"
    },
    {
      "depth": 2,
      "text": "How do you get tokens_per_audio_minute from a pilot?",
      "anchor": "how-do-you-get-tokens-per-audio-minute-from-a-pilot",
      "url": "https://changegamer.ai/articles/voice-agent-cost-per-minute#how-do-you-get-tokens-per-audio-minute-from-a-pilot"
    },
    {
      "depth": 2,
      "text": "Where do silence, retries and tool calls add cost?",
      "anchor": "where-do-silence-retries-and-tool-calls-add-cost",
      "url": "https://changegamer.ai/articles/voice-agent-cost-per-minute#where-do-silence-retries-and-tool-calls-add-cost"
    },
    {
      "depth": 2,
      "text": "Which variables move the result most?",
      "anchor": "which-variables-move-the-result-most",
      "url": "https://changegamer.ai/articles/voice-agent-cost-per-minute#which-variables-move-the-result-most"
    },
    {
      "depth": 2,
      "text": "What should you do before quoting a number?",
      "anchor": "what-should-you-do-before-quoting-a-number",
      "url": "https://changegamer.ai/articles/voice-agent-cost-per-minute#what-should-you-do-before-quoting-a-number"
    }
  ],
  "faq": [
    {
      "question": "How much does a voice AI agent cost per minute?",
      "answer": "No honest single figure exists, because cost per minute depends on audio tokens per minute, how long the agent talks, retries and tool calls. Compute it from usage recorded in a pilot with real callers, multiplied by your vendor's rate card as of the pilot date, rather than quoting a blog number."
    },
    {
      "question": "What are the OpenAI realtime audio token prices?",
      "answer": "The voice-realtime-agents reference records roughly $32 per 1M input tokens and $64 per 1M output tokens for the full OpenAI realtime model, and $10 and $20 for the mini, web-verified on 2026-07-09 and not re-verified on 2026-09-28. Check the vendor's pricing page before budgeting."
    },
    {
      "question": "Is a cascaded voice agent cheaper than speech-to-speech?",
      "answer": "The corpus does not say. It states only that a cascade pays for three model calls per turn and that native audio tokens are expensive. Which is cheaper for your traffic depends on measured usage and each vendor's rate card, so compute both formulas from the same pilot calls."
    },
    {
      "question": "Do I pay for silence in a voice agent call?",
      "answer": "The corpus does not state how any vendor bills silence. As the author's inference, a session that streams microphone audio continuously may count silent input as input tokens, so check the usage field of a call that contained long pauses before assuming silence is free."
    }
  ],
  "body": "This article shows how to compute a voice agent cost per minute from your own measurements, and it cannot give you the number itself. The corpus holds no total-cost figure for a call, and the [voice AI agent in production](/articles/voice-ai-agent-in-production) pillar already says so in its cost section; here the job is the method that replaces the missing number.\n\nLabels used below: \"corpus\" means a claim from a named reference, \"inference\" means the author's reasoning with no published source. Every formula and the worked example are inference. The example uses arbitrary placeholder units and is not a price.\n\n## What can the corpus tell you about voice agent pricing?\n\nThe corpus gives three usable inputs and nothing that adds up to a per-minute price. All three come from the [voice and realtime agents reference](/resources/voice-realtime-agents), whose vendor facts were web-verified on 2026-07-09 and not re-verified on 2026-09-28.\n\n| Input | Value | Status |\n|---|---|---|\n| OpenAI realtime audio, full model | about $32 per 1M input tokens, $64 per 1M output tokens | corpus, verified 2026-07-09, not re-verified 2026-09-28 |\n| OpenAI realtime audio, mini | about $10 per 1M input tokens, $20 per 1M output tokens | corpus, same dates |\n| Audio versus text token price | roughly 3 to 10 times | corpus (voice-realtime-agents, verified 2026-07-09); check your vendor |\n\nArithmetic on those list prices: the full model costs 3.2 times the mini on both the input and the output side. Prices can change without notice, so treat them as a shape, not a quote. The corpus holds no rate card for any speech-to-text or text-to-speech vendor, and no figure for tokens per minute of audio.\n\n## What is the formula for a native speech-to-speech agent?\n\nFor a native speech-to-speech agent, cost per minute is audio input tokens plus audio output tokens plus any text tokens, each multiplied by its own price. As inference, in symbols:\n\n```text\ncost_per_min = tokens_per_audio_minute * in_share  * price_audio_in\n             + tokens_per_audio_minute * talk_ratio * price_audio_out\n             + text_tokens_per_min_in  * price_text_in\n             + text_tokens_per_min_out * price_text_out\n```\n\n- **tokens_per_audio_minute** is how many tokens one minute of audio becomes. Do not assume it: the corpus gives none, and it may differ between input and output and between vendors.\n- **in_share** is the fraction of each call minute in which audio is sent to the model. If the microphone streams continuously, it is 1.0 whether or not the caller speaks.\n- **talk_ratio** is the fraction of each call minute the agent itself is speaking.\n- **text_tokens** cover system prompt, tool schemas, tool results and any history the vendor counts as text.\n\nKeep audio and text as separate counts because the two are priced differently. The general compounding model in the [agent cost and latency optimization reference](/resources/agent-cost-latency-optimization), cost roughly tokens per call times price times N calls, is the same idea with a turn count; the formula above just spells out the audio terms.\n\n## What is the formula for a cascaded agent?\n\nFor a cascaded agent, cost per minute is the sum of three stage costs, each priced by its own vendor. The corpus confirms the shape, three sequential model calls per turn, and nothing about how any vendor bills; stage pricing is outside it. In symbols (inference):\n\n```text\ncost_per_min = stt_rate * stt_minutes_per_min\n             + turns_per_min * (llm_in * price_llm_in + llm_out * price_llm_out)\n             + tts_rate * tts_units_per_min\n```\n\n- **stt_rate** and **tts_rate** are whatever unit each vendor bills (audio seconds, characters or something else); read each rate card and use its unit, not an assumed one.\n- **llm_out** is the generated text tokens per turn; **tts_units_per_min** is the amount of speech synthesized per minute of call, in whatever unit the TTS vendor bills.\n- **turns_per_min** is your measured turn count divided by call minutes.\n- **llm_in** includes the system prompt, tool schemas and the earlier turns of the conversation, so it grows through the call.\n\nA cascade also lets you swap the model in each term independently, which is the control the corpus credits to the architecture. The decision between the two designs is covered in [what to log and filter in a voice agent, by architecture](/articles/voice-agent-architecture-cascaded-vs-speech-to-speech).\n\n## How do you get tokens_per_audio_minute from a pilot?\n\nGet it by measuring: run a pilot with real callers and divide each call's reported audio token usage by its length in minutes. The corpus does not describe any vendor's usage fields, so read your vendor's response documentation for what it returns, and treat the steps as inference.\n\n1. Run a pilot of real calls, including noisy, interrupted and silent ones.\n2. Log, per call, the audio input tokens, audio output tokens, text input tokens, text output tokens and call duration, as separate numbers.\n3. Compute T per call as audio tokens divided by audio minutes, separately for input and output.\n4. Look at the distribution, not the mean: the shortest calls and the longest calls will disagree.\n5. Re-run after any prompt, voice or model change, because T and history size may move.\n\nHow to record and price these counts safely, including versioning the price table, is in [agent cost telemetry in production](/articles/agent-cost-telemetry-in-production), which this article does not repeat. Cluster-wide guidance on measuring per call is in the pillar.\n\n## Where do silence, retries and tool calls add cost?\n\nSilence, retries and tool-call turns can each add billable input without adding useful conversation, and all three are inference until your pilot confirms them.\n\n- **Idle audio.** A session that streams microphone audio during pauses, hold or background noise may bill that audio as input. Test with a call that is mostly silence and compare its usage to its length. The corpus says the 2.1 realtime models improved \"noise/silence handling\", which is a quality claim, not a billing one.\n- **Retries.** If a caller is misheard and repeats, or the agent re-asks, the repeated turn is paid twice. Count repeated turns as a metric next to turn count.\n- **Tool-call turns.** A tool call may add a model step before the spoken reply, and the tool result goes back into the context as text. Whether a vendor bills that step as a separate response is not stated in the corpus; check one call with tools against one without. Tool design is covered in [function calling in a voice agent](/articles/tools-in-a-voice-agent-loop).\n- **History.** If the full conversation is re-read on each turn, input grows with turn number, so long calls cost more per minute than short ones. Confirm with the usage of the last turn of a long call.\n\n## Which variables move the result most?\n\nThe variables that appear in more than one term or multiply an entire term move the result most, and a sensitivity check on your own pilot data will rank them. The ranking below is inference from the structure of the formulas, not a measurement.\n\n| Variable | Effect on cost per minute | How to test |\n|---|---|---|\n| tokens_per_audio_minute | Scales every audio term proportionally | Measure from the pilot usage field |\n| in_share | Scales the whole input term; 1.0 means silence counts | Compare a silent call to a talkative one |\n| talk_ratio | Scales only the output term | Tally agent speech time per call |\n| Output versus input price | Decides how much a talkative agent costs | Read the rate card for both sides |\n| Model tier | Full versus mini is 3.2 times on both list prices (corpus arithmetic) | Re-price the same pilot calls |\n| History growth | Raises per-minute cost in long calls | Plot cost by turn number |\n\nWorked example with arbitrary placeholder units, not dollars and not a real result: set tokens_per_audio_minute to 1 unit, in_share to 1.0, talk_ratio to 0.4, input price to 1 and output price to 2, and ignore text. Input term: 1.0. Output term: 0.8. Total: 1.8 units, of which the output term is about 44%. Doubling talk_ratio to 0.8 raises the total to 2.6, a rise of about 44%; halving in_share to 0.5 lowers it to 1.3, a fall of about 28%. These numbers show how to read a sensitivity, nothing about real calls.\n\n## What should you do before quoting a number?\n\nBefore quoting any cost per minute, price your pilot twice, once per architecture, from the same recorded calls, and publish the range with its date. Concretely:\n\n- Record the vendor, model, rate-card date and the pilot's call count next to the figure.\n- Report a distribution (median and a high percentile) as the pillar's per-call advice suggests, not an average alone.\n- Add the non-model costs the corpus does not cover, such as telephony minutes and human handoff, which are outside these formulas. See [voice agent human handoff](/articles/voice-agent-human-handoff).\n- Check latency alongside cost, since cheaper stages often change the [voice agent latency budget](/articles/voice-agent-latency-budget).\n- Re-verify the OpenAI list prices: the corpus figures were verified 2026-07-09 and not re-verified 2026-09-28.\n\nAs of October 2026, ChangeGamer runs no voice agent, so there is no measured per-minute figure here, and none should be inferred from the placeholders above.",
  "cluster": {
    "id": "voice-agents-in-production",
    "title": "Voice agents in production",
    "description": "How to build and run a live voice AI agent — architecture choice, turn detection and barge-in, latency budget, tool calls in a voice loop, transport, cost, human handoff, guardrails, monitoring and launch — covering live caller conversations only, not offline dubbing/localization (ai-dubbing-localization-and-subtitling) and not the WER/MOS/VoiceBench scoring methodology owned by the evaluating-voice-agents resource.",
    "status": "complete",
    "pillar": {
      "slug": "voice-ai-agent-in-production",
      "title": "Voice AI Agent in Production: Architecture, Latency, Handoff and Launch",
      "description": "How to build and run a voice AI agent in production: cascaded vs speech-to-speech architecture, turn detection and barge-in, the latency budget, tool calls in a voice loop, transport, cost, human handoff and launch sequencing.",
      "kind": "pillar",
      "order": 0,
      "html": "https://changegamer.ai/articles/voice-ai-agent-in-production",
      "markdown": "https://changegamer.ai/articles/voice-ai-agent-in-production.md",
      "json": "https://changegamer.ai/api/articles/voice-ai-agent-in-production.json"
    },
    "articles": [
      {
        "slug": "voice-agent-latency-budget",
        "title": "Voice Agent Latency Budget: Where the 600 ms Goes and How to Hold It",
        "description": "How to split a 600 ms voice agent latency budget across speech-to-text, the language model, speech synthesis and tool calls, how to measure each stage, and which levers hold the budget.",
        "kind": "sub",
        "order": 1,
        "html": "https://changegamer.ai/articles/voice-agent-latency-budget",
        "markdown": "https://changegamer.ai/articles/voice-agent-latency-budget.md",
        "json": "https://changegamer.ai/api/articles/voice-agent-latency-budget.json"
      },
      {
        "slug": "voice-turn-detection-and-barge-in-testing",
        "title": "How to Test Voice Agent Turn Detection and Barge-In",
        "description": "How to test voice agent turn detection and barge-in: build a labelled clip set, count barge-in accuracy and false-interruption rate, separate cut-off from talk-over failures, and split offline gates from online monitors.",
        "kind": "sub",
        "order": 2,
        "html": "https://changegamer.ai/articles/voice-turn-detection-and-barge-in-testing",
        "markdown": "https://changegamer.ai/articles/voice-turn-detection-and-barge-in-testing.md",
        "json": "https://changegamer.ai/api/articles/voice-turn-detection-and-barge-in-testing.json"
      },
      {
        "slug": "voice-agent-architecture-cascaded-vs-speech-to-speech",
        "title": "What to Log and Filter in a Voice Agent, by Architecture",
        "description": "What to log and filter in a voice agent depending on architecture: where a cascaded pipeline gives you text seams for logging, redaction and output filters, what a native speech-to-speech model leaves you to do from outside, and what a model swap forces you to re-test.",
        "kind": "sub",
        "order": 3,
        "html": "https://changegamer.ai/articles/voice-agent-architecture-cascaded-vs-speech-to-speech",
        "markdown": "https://changegamer.ai/articles/voice-agent-architecture-cascaded-vs-speech-to-speech.md",
        "json": "https://changegamer.ai/api/articles/voice-agent-architecture-cascaded-vs-speech-to-speech.json"
      },
      {
        "slug": "tools-in-a-voice-agent-loop",
        "title": "Function Calling in a Voice Agent: What a Tool May Be in a Spoken Loop",
        "description": "Function calling in a voice agent: which vendors and frameworks support tools as of the corpus's 2026-07-09 verification, how to classify tools as lookup, action or handoff, what barge-in does to a side effect, and a checklist for admitting a tool.",
        "kind": "sub",
        "order": 4,
        "html": "https://changegamer.ai/articles/tools-in-a-voice-agent-loop",
        "markdown": "https://changegamer.ai/articles/tools-in-a-voice-agent-loop.md",
        "json": "https://changegamer.ai/api/articles/tools-in-a-voice-agent-loop.json"
      },
      {
        "slug": "voice-agent-transport-webrtc-vs-websocket-vs-sip",
        "title": "Voice Agent Transport: WebRTC vs WebSocket, and Where SIP Fits",
        "description": "WebRTC vs WebSocket for voice AI agents: which transport each vendor documents as of the corpus's 2026-07-09 verification, how cascaded stacks use WebSocket components, a decision tree by client type, and a per-transport test checklist.",
        "kind": "sub",
        "order": 5,
        "html": "https://changegamer.ai/articles/voice-agent-transport-webrtc-vs-websocket-vs-sip",
        "markdown": "https://changegamer.ai/articles/voice-agent-transport-webrtc-vs-websocket-vs-sip.md",
        "json": "https://changegamer.ai/api/articles/voice-agent-transport-webrtc-vs-websocket-vs-sip.json"
      },
      {
        "slug": "voice-agent-human-handoff",
        "title": "Voice Agent Human Handoff: What Happens on the Call When the Agent Lets Go",
        "description": "Voice agent human handoff mechanics: the handoff as a tool that ends the agent's session, barge-in during the transfer announcement, what the caller hears on hold and on failure, a context payload schema, and a real-call test checklist.",
        "kind": "sub",
        "order": 6,
        "html": "https://changegamer.ai/articles/voice-agent-human-handoff",
        "markdown": "https://changegamer.ai/articles/voice-agent-human-handoff.md",
        "json": "https://changegamer.ai/api/articles/voice-agent-human-handoff.json"
      },
      {
        "slug": "voice-agent-cost-per-minute",
        "title": "How to Compute Your Voice Agent Cost per Minute",
        "description": "How to compute a voice agent cost per minute from your own pilot: symbolic formulas for native speech-to-speech and cascaded STT, LLM and TTS, the variables that move the result, idle audio, retries, tool-call turns, and a sensitivity check.",
        "kind": "sub",
        "order": 7,
        "html": "https://changegamer.ai/articles/voice-agent-cost-per-minute",
        "markdown": "https://changegamer.ai/articles/voice-agent-cost-per-minute.md",
        "json": "https://changegamer.ai/api/articles/voice-agent-cost-per-minute.json"
      },
      {
        "slug": "guardrails-for-spoken-output-in-voice-agents",
        "title": "Voice Agent Guardrails: Checking What the Agent Says Before the Caller Hears It",
        "description": "Voice agent guardrails for spoken output: sentence-level gating before TTS, fail-closed judges, spoken numbers a text PII filter misses, readback before state changes, transcription-driven injection, refusal phrasing for the ear, and an adversarial test list.",
        "kind": "sub",
        "order": 8,
        "html": "https://changegamer.ai/articles/guardrails-for-spoken-output-in-voice-agents",
        "markdown": "https://changegamer.ai/articles/guardrails-for-spoken-output-in-voice-agents.md",
        "json": "https://changegamer.ai/api/articles/guardrails-for-spoken-output-in-voice-agents.json"
      },
      {
        "slug": "voice-agent-online-monitoring",
        "title": "How to Monitor a Voice Agent in Production: Dashboard, Alerts and Runbook",
        "description": "How to monitor a voice agent in production: per-stage latency percentiles, transcription confidence, containment paired with a resolution signal, live false-interruption rate, a handoff trigger review, and call-audio retention, each with what to chart, alert on and do.",
        "kind": "sub",
        "order": 9,
        "html": "https://changegamer.ai/articles/voice-agent-online-monitoring",
        "markdown": "https://changegamer.ai/articles/voice-agent-online-monitoring.md",
        "json": "https://changegamer.ai/api/articles/voice-agent-online-monitoring.json"
      },
      {
        "slug": "voice-agent-vendor-change-management",
        "title": "How to Handle Voice AI Vendor Model Changes Without Regressing Callers",
        "description": "How to handle voice AI vendor model changes: classify the change, record the model id on every trace, replay an offline set with hard calls on old and new, canary before cutover, keep a rollback, and run a deprecation-readiness routine.",
        "kind": "sub",
        "order": 10,
        "html": "https://changegamer.ai/articles/voice-agent-vendor-change-management",
        "markdown": "https://changegamer.ai/articles/voice-agent-vendor-change-management.md",
        "json": "https://changegamer.ai/api/articles/voice-agent-vendor-change-management.json"
      },
      {
        "slug": "voice-agent-launch-checklist",
        "title": "Voice Agent Launch Checklist: The Go/No-Go Gates Before Real Callers",
        "description": "A voice agent launch checklist as yes/no gates: scope, offline replay, per-stage latency, barge-in, tools, transport, handoff, cost, guardrails, monitoring and rollback, each with a pass signal and the article that owns the method.",
        "kind": "sub",
        "order": 11,
        "html": "https://changegamer.ai/articles/voice-agent-launch-checklist",
        "markdown": "https://changegamer.ai/articles/voice-agent-launch-checklist.md",
        "json": "https://changegamer.ai/api/articles/voice-agent-launch-checklist.json"
      },
      {
        "slug": "voice-agent-multilingual-callers",
        "title": "How Does a Voice Agent Handle Callers Who Speak Another Language?",
        "description": "How a live voice agent handles callers who speak another language: detecting the language, choosing speech components per language, slicing evaluation by language and handing off when the language is unsupported, with the thin corpus evidence stated plainly.",
        "kind": "sub",
        "order": 12,
        "html": "https://changegamer.ai/articles/voice-agent-multilingual-callers",
        "markdown": "https://changegamer.ai/articles/voice-agent-multilingual-callers.md",
        "json": "https://changegamer.ai/api/articles/voice-agent-multilingual-callers.json"
      }
    ]
  },
  "navigation": {
    "pillar": {
      "slug": "voice-ai-agent-in-production",
      "title": "Voice AI Agent in Production: Architecture, Latency, Handoff and Launch",
      "description": "How to build and run a voice AI agent in production: cascaded vs speech-to-speech architecture, turn detection and barge-in, the latency budget, tool calls in a voice loop, transport, cost, human handoff and launch sequencing.",
      "kind": "pillar",
      "order": 0,
      "html": "https://changegamer.ai/articles/voice-ai-agent-in-production",
      "markdown": "https://changegamer.ai/articles/voice-ai-agent-in-production.md",
      "json": "https://changegamer.ai/api/articles/voice-ai-agent-in-production.json"
    },
    "previous": {
      "slug": "voice-agent-human-handoff",
      "title": "Voice Agent Human Handoff: What Happens on the Call When the Agent Lets Go",
      "description": "Voice agent human handoff mechanics: the handoff as a tool that ends the agent's session, barge-in during the transfer announcement, what the caller hears on hold and on failure, a context payload schema, and a real-call test checklist.",
      "kind": "sub",
      "order": 6,
      "html": "https://changegamer.ai/articles/voice-agent-human-handoff",
      "markdown": "https://changegamer.ai/articles/voice-agent-human-handoff.md",
      "json": "https://changegamer.ai/api/articles/voice-agent-human-handoff.json"
    },
    "next": {
      "slug": "guardrails-for-spoken-output-in-voice-agents",
      "title": "Voice Agent Guardrails: Checking What the Agent Says Before the Caller Hears It",
      "description": "Voice agent guardrails for spoken output: sentence-level gating before TTS, fail-closed judges, spoken numbers a text PII filter misses, readback before state changes, transcription-driven injection, refusal phrasing for the ear, and an adversarial test list.",
      "kind": "sub",
      "order": 8,
      "html": "https://changegamer.ai/articles/guardrails-for-spoken-output-in-voice-agents",
      "markdown": "https://changegamer.ai/articles/guardrails-for-spoken-output-in-voice-agents.md",
      "json": "https://changegamer.ai/api/articles/guardrails-for-spoken-output-in-voice-agents.json"
    }
  },
  "resources": [
    {
      "slug": "voice-realtime-agents",
      "html": "https://changegamer.ai/resources/voice-realtime-agents",
      "markdown": "https://changegamer.ai/resources/voice-realtime-agents.md",
      "json": "https://changegamer.ai/api/resources/voice-realtime-agents.json"
    },
    {
      "slug": "agent-cost-latency-optimization",
      "html": "https://changegamer.ai/resources/agent-cost-latency-optimization",
      "markdown": "https://changegamer.ai/resources/agent-cost-latency-optimization.md",
      "json": "https://changegamer.ai/api/resources/agent-cost-latency-optimization.json"
    }
  ]
}