Audio Cost · for voice agents, transcription, TTS

What do voice + audio workloads cost?

Transcription, TTS, and audio-in-LLM pricing. Build voice agents, transcribe podcasts, or stream audio to multimodal LLMs.

Pricing verified: 2026-07-28 Whisper · Deepgram · ElevenLabs · Gemini
What this calculator does

Speech-to-text and text-to-speech cost per minute of audio.

Why use it
  • STT/TTS cost is usually billed per minute, not per token — easy to miscalculate
  • Compare Whisper, Deepgram, ElevenLabs, Cartesia side-by-side

New to this calculator? Start with the ⚡ Playground — a few sliders, instant ballpark. Then switch to the 🧮 Calculator for your exact number.

Two ways to use this: visualize in the Playground, then get your number in the Calculator.

▶Playground A quick, visual way to see which factors move your result the most. Open the playground → ▤Calculator Enter your real workload for a precise result you can apply to your own usage. Go to the calculator →
Audio Cost Playground
Drag the sliders for an instant estimate.
What will audio / voice cost?

Three streams: speech-to-text in, the realtime voice agent, and text-to-speech out. Per-unit rates fixed at current market prices.

Estimated monthly cost
—
Change the input sliders below to see new estimates.

How we got this estimate
—

💡Total = STT (minutes) + voice agent (the share you route live) + TTS (characters). Live voice-native is the priciest stream.

📋 Example Workload - change any field to see your actual cost

Audio Cost Calculator

Enter your exact numbers for a precise result.
📊 Not sure of a value? Fields with a ▾ Typical pill offer broad industry ballparks (sourced typical ranges; Mid-2026 voice stack: streaming STT mainstream $0.0025-0.012/min (Deepgram Nova-3 ~$0.0048-0.0077, Whisper/GPT-4o-transcribe $0.006, GPT-4o-mini $0.003); realtime voice-agent bundles ~$0.06/min (OpenAI gpt-realtime) to $0.08/min (Deepgram Voice Agent API); TTS spans $0.004-0.016/1K chars (hyperscalers) to $0.030 (Aura-2 class) to $0.30 (premium ElevenLabs-class voices).) so you can move forward now — your result gets more accurate as you replace them with your own measured numbers. Values marked * are rough estimates.
🎮 Interactive Guide & Calculator Playground →
🎤 Transcription (STT)
🔊 Text-to-Speech (TTS)
🗣 Voice agent (full loop)
Speech-to-text, text-to-speech and realtime voice all price differently. Enter your audio workload below for a true monthly cost.
🎛 CALCULATOR
🎤 Your transcription workload

Converting speech to text. Billed per minute of audio.

Hint: Which speech-to-text service. Its rate shows in the note below.
Hint: Hours of recordings you transcribe per month. 100 hrs ~ one full-time call-center agent.
Load preset

Results

Monthly transcription cost
-
-
Per minute
-
Per hour
-
Annual
-
📊 Compare all transcription services
Service $/min Monthly Annual
🔊 Your TTS workload

Converting text to speech. Billed per character of text.

Hint: Which text-to-speech voice service. Its rate shows in the note below.
Hint: Characters of speech made per month. 1M chars ~ 150K words; a 5-min call ~ 5,000 chars.
Load preset

Results

Monthly TTS cost
-
-
Per 1K chars
-
Per 1M chars
-
Annual
-
📊 Compare all TTS providers
Service $/M chars Monthly Annual
🗣 Full voice agent loop

Transcription + LLM reasoning + TTS. The real cost of a voice bot call.

Hint: The service that turns caller speech into text.
Hint: The brain that decides what the bot says back.
Hint: The voice that speaks the bot's replies aloud.
Hint: Average length of one call, in minutes.
Hint: How fast the caller talks (words/min). 80-130 typical; leave as-is if unsure.
Hint: How fast the bot talks (words/min). Leave as-is if unsure.
Hint: Calls the bot handles per day at your busiest.

Results

Monthly voice agent cost
-
-
Per call
-
Per minute
-
Annual
-
💡 Breakdown per call
ComponentCost% of call
🎯 Optimization notes
    Vision cost → Text-agent cost → Text-only calculator →
    🎯 Use this result to
    • 🎤 Pick STT and TTS providers — Deepgram, AssemblyAI, OpenAI, ElevenLabs all priced differently. Decide right.
    • 🤖 Cost a voice agent stack — STT + LLM + TTS + latency engineering. See full per-minute cost.
    • 📉 Find scale break-even — At certain volumes, self-host beats managed. Calc surfaces the threshold.
    • 🔌 Integrate with your AI agents — MCP available for agentic workflow integration. Cost-aware audio routing.
    📅 Schedule a call to apply this to your workload

    Go deeper

    Our playbooks on cutting this number.

    🖼
    Vision Cost
    Multimodal image pricing
    🤖
    Agent Loop Cost
    Text agent economics
    🔀
    Multi-Model Router
    Route voice calls by complexity
    🧮
    Cost Calculator
    Text-only baseline

    Need help using this calculator for your workloads?

    AICost.ai has 50+ calculators and playbooks. Schedule an AvatarVA meeting and we'll work through your real cost scenarios across AI & Cloud: visibility, cost reduction, optimization, forecasting and capacity planning, without sacrificing accuracy or performance.

    📅 Schedule an AvatarVA meeting →
    📖 Data sources & methodology 163 text models · 9 embeddings · 37 vision · 55 audio · 8 vector DBs across 10 vendor pages · last verified 2026-07-28

    Methodology

    • All prices are USD per 1 million tokens, current as of 2026-07-28.
    • Vendor-published values have no mark. Inferred/extrapolated values are marked with * and listed below.
    • Batch API discounts are 50% off standard rates across providers that offer Batch mode.
    • Prompt caching discounts vary by provider (typically 80-90% off cached input tokens).
    • Regional data-residency surcharges (Anthropic 1.1x, OpenAI 1.1x, Google regional tiers) are NOT included in base rates.
    • Long-context pricing tiers apply when input exceeds model threshold.
    • Embedding prices are input-only (no output tokens generated).

    Primary sources

    Last-verified date is the most recent successful daily snapshot (aicost_pricing_snapshots) or, when no snapshot exists yet, the latest successful crawler run (aicost_crawler_runs). 10 of 10 vendors are currently verified. Aggregator services (TokenCost, AI Pricing Guru, etc.) are not listed.

    Anthropic
    2026-07-28
    https://www.anthropic.com/pricing
    Daily snapshot since Sep 2023 · 631 days captured
    Anthropic Docs
    2026-07-28
    https://platform.claude.com/docs/en/about-claude/pricing
    Daily snapshot since Sep 2023 · 631 days captured
    OpenAI
    2026-07-28
    https://openai.com/api/pricing/
    Daily snapshot since Sep 2023 · 632 days captured
    Google AI
    2026-07-28
    https://ai.google.dev/gemini-api/docs/pricing
    Daily snapshot since Dec 2023 · 607 days captured
    Google Vertex
    2026-07-28
    https://cloud.google.com/vertex-ai/generative-ai/pricing
    Daily snapshot since Dec 2023 · 607 days captured
    DeepSeek
    2026-07-28
    https://api-docs.deepseek.com/quick_start/pricing
    Daily snapshot since May 2024 · 546 days captured
    xAI
    2026-07-28
    https://x.ai/api
    Daily snapshot since Nov 2024 · 464 days captured
    Mistral
    2026-07-28
    https://mistral.ai/pricing
    Daily snapshot since Dec 2023 · 605 days captured
    Cohere
    2026-07-28
    https://cohere.com/pricing
    Daily snapshot since Sep 2023 · 631 days captured
    Voyage AI
    2026-07-28
    https://docs.voyageai.com/docs/pricing

    Inferred values (marked with * in calculator tables)

    Derived from industry conventions, not directly published by the vendor. Typical conventions: cached input = 10% of base (90% off), Batch API = 50% of base (50% off).

    Vendor / Model Field Why it’s inferred
    Anthropic — Claude Sonnet 4.6 cachedInput Derived at 10% of input rate — Anthropic publishes 90% cache-hit discount on this tier.
    Anthropic — Claude Sonnet 4.5 cachedInput Derived at 10% of input rate; same 90% cache-hit convention as Sonnet 4.6.
    Anthropic — Claude Sonnet 4.5 batchInput Derived at 50% of standard input — Anthropic documents uniform 50% Batch discount.
    Anthropic — Claude Sonnet 4.5 batchOutput Derived at 50% of standard output — Anthropic documents uniform 50% Batch discount.
    Anthropic — Claude Haiku 4.5 cachedInput Derived at 10% of input rate — Anthropic 90% cache-hit discount convention.
    OpenAI — GPT-5.4 Mini cachedInput Derived at 10% of input — OpenAI documents automatic 90% discount on cache hits across GPT-5.x tier.
    OpenAI — GPT-5.4 Nano cachedInput Derived at 10% of input — OpenAI 90% cache-hit convention.
    OpenAI — GPT-5.4 Nano batchInput Derived at 50% of input — OpenAI Batch API uniform 50% discount.
    OpenAI — GPT-5.4 Nano batchOutput Derived at 50% of output — OpenAI Batch API uniform 50% discount.
    OpenAI — GPT-5.4 Pro cachedInput Derived at 10% of input — OpenAI 90% cache-hit convention.
    OpenAI — GPT-5.4 Pro batchInput Derived at 50% of input — OpenAI Batch API uniform 50% discount.
    OpenAI — GPT-5.4 Pro batchOutput Derived at 50% of output — OpenAI Batch API uniform 50% discount.
    OpenAI — GPT-5.2 cachedInput Derived at 10% of input; no residency uplift.
    OpenAI — GPT-5.2 batchInput Derived at 50% of input.
    OpenAI — GPT-5.2 batchOutput Derived at 50% of output.
    OpenAI — GPT-5 cachedInput Derived at 10% of input.
    OpenAI — GPT-5 batchInput Derived at 50% of input.
    OpenAI — GPT-5 batchOutput Derived at 50% of output.
    OpenAI — GPT-5.5 Pro cachedInput Derived at 10% of input — OpenAI does not publish a cached rate for *-pro models; using the family convention.
    OpenAI — GPT-5.5 Pro batchInput Derived at 50% of input.
    OpenAI — GPT-5.5 Pro batchOutput Derived at 50% of output.
    OpenAI — GPT-5.2 Pro cachedInput Derived at 10% of input — pro-tier convention.
    OpenAI — GPT-5.2 Pro batchInput Derived at 50% of input.
    OpenAI — GPT-5.2 Pro batchOutput Derived at 50% of output.
    OpenAI — GPT-5.1 batchInput Derived at 50% of input.
    OpenAI — GPT-5.1 batchOutput Derived at 50% of output.
    OpenAI — GPT-5 Pro batchInput Derived at 50% of input.
    OpenAI — GPT-5 Pro batchOutput Derived at 50% of output.
    OpenAI — GPT-5 Nano cachedInput Derived at 10% of input.
    OpenAI — GPT-5 Nano batchInput Derived at 50% of input.
    OpenAI — GPT-5 Nano batchOutput Derived at 50% of output.
    Google — Gemini 3 Flash cachedInput Derived at 10% of input — Google caching discount convention ~90%.
    Google — Gemini 3.1 Flash-Lite cachedInput Derived at 10% of input — Google caching convention.
    Google — Gemini 3.1 Flash-Lite batchInput Derived at 50% of input — Google Batch API uniform 50% discount.
    Google — Gemini 3.1 Flash-Lite batchOutput Derived at 50% of output — Google Batch API uniform 50% discount.
    Google — Gemini 2.5 Pro cachedInput Derived at 10% of input.
    Google — Gemini 2.5 Flash cachedInput Derived at 10% of input.
    Google — Gemini 2.5 Flash-Lite cachedInput Derived at 10% of input — Google caching convention.
    Google — Gemini 2.5 Flash-Lite batchInput Derived at 50% of input — Google Batch API uniform 50% discount.
    Google — Gemini 2.5 Flash-Lite batchOutput Derived at 50% of output — Google Batch API uniform 50% discount.
    Google — Gemini 2.0 Flash cachedInput Derived at 25% of input per Google 2.0 family caching rates.
    Google — Gemini 2.0 Flash batchInput Derived at 50% of input — Google Batch API uniform 50% discount.
    Google — Gemini 2.0 Flash batchOutput Derived at 50% of output — Google Batch API uniform 50% discount.
    Google — Gemini 2.0 Flash-Lite cachedInput Derived at 10% of input — Google caching convention.
    Google — Gemini 2.0 Flash-Lite batchInput Derived at 50% of input — Google Batch API uniform 50% discount.
    Google — Gemini 2.0 Flash-Lite batchOutput Derived at 50% of output — Google Batch API uniform 50% discount.
    xAI — Grok 4 (legacy) cachedInput Extrapolated at 25% of base.

    Pricing is cross-verified against the LiteLLM community registry when available. Daily snapshots are kept in aicost_pricing_snapshots; every change is logged to aicost_price_changelog with old & new values for full audit trail. Read the full methodology →