Un’unica chiave per tutte le API di Zoom AI Services. Nessun impegno minimo. Consulta i tassi di consumo dei crediti, le tariffe di configurazione e i componenti aggiuntivi facoltativi per ogni API, con la possibilità di stimare i costi prima di iniziare lo sviluppo.
Transcription, speech synthesis, and real-time voice.
Scribe (Speech-to-text)
Turn recorded or live audio into speaker-aware text ready for search, automation, and analysis.
Base API usage$0.20
Add-on usage$0.00
Estimated monthly total$0.20
List rates in USD, before taxes. Displayed estimates are rounded to the nearest cent and calculated using per-minute rates. Credits, discounts, and third-party service costs are not included. Questa è solo una stima a scopo illustrativo e gli importi effettivamente fatturati possono variare a causa degli arrotondamenti di fatturazione e delle condizioni dell’account. Consulta il listino dei crediti per i prezzi attuali al minuto.
Scribe (Speech-to-text) rates in USD
Mode
Per hour
About hourly rates
Le tariffe orarie sono calcolate a partire dalle tariffe al minuto e arrotondate al centesimo più vicino per la visualizzazione. La fatturazione si basa sulle tariffe al minuto. Consulta il listino dei crediti per i prezzi attuali al minuto.
Per minute
Fast
Scribe (Speech-to-text) · Fast
Scribe API Fast converts audio to text in seconds with enterprise-grade accuracy for real-time applications.
Description of Metering: Usage is measured based on the total duration of audio processed in minutes during a given billing period.
For example, if you submit ten (10) audio files that are each 30 minutes long for fast transcription, then 300 total minutes will be used and billed at $0.0033/min = $0.99 total.
$0.20
$0.0033
Batch
Scribe (Speech-to-text) · Batch
Scribe API Batch processes thousands of audio files and converts audio to text for scalable transcription workflows.
Description of Metering: Usage is measured based on the total duration of audio processed in minutes during a given billing period.
For example, if you submit ten (10) call recordings that are each 30 minutes long for batch transcription, then 300 total minutes will be used and billed at $0.0025/min = $0.75 total.
$0.15
$0.0025
Live
Scribe (Speech-to-text) · Live
Scribe API Live delivers real-time audio-to-text transcription, designed for near real-time streaming, returning a transcript segment after each detected speech turn via a streaming WebSocket connection, purpose-built for live applications requiring real-time speech recognition.
Description of Metering: Usage is measured based on the total duration of audio processed in minutes during a given billing period.
For example, if you run ten (10) live transcription sessions that are each 30 minutes long, then 300 total minutes will be used and billed at $0.0042/min = $1.26 total.
$0.25
$0.0042
Pro High-Accuracy / Multilingual Fast
Scribe (Speech-to-text) · Pro High-Accuracy / Multilingual Fast
Scribe API Pro High-Accuracy / Multilingual (Fast) is a lightweight multimodal model that provides high-precision transcription from speech to text in seconds.
Description of Metering: Usage is measured based on the total duration of audio transcribed using the Scribe Pro high-accuracy model in minutes during a given billing period.
For example, if you run ten (10) fast transcription jobs that are each 30 minutes long using the Scribe Pro model, then 300 total minutes will be used and billed at $0.0058/min (Scribe Pro High-Accuracy) = $1.74 total.
$0.35
$0.0058
Pro High-Accuracy / Multilingual Batch
Scribe (Speech-to-text) · Pro High-Accuracy / Multilingual Batch
Scribe API Pro High-Accuracy / Multilingual (Batch) is a lightweight multimodal model that provides high-precision transcription from speech to text.
Description of Metering: Usage is measured based on the total duration of audio transcribed using the Scribe Pro high-accuracy model in minutes during a given billing period.
For example, if you batch transcribe ten (10) audio files that are each 30 minutes long using the Scribe Pro model, then 300 total minutes will be used and billed at $0.005/min (Scribe Pro High-Accuracy) = $1.50 total.
$0.30
$0.005
Pro High-Accuracy / Multilingual Live
Scribe (Speech-to-text) · Pro High-Accuracy / Multilingual Live
Scribe API Pro High-Accuracy / Multilingual (Live) is a lightweight multimodal model that provides high-precision transcription from speech to text with near real-time streaming.
Description of Metering: Usage is measured based on the total duration of audio processed using the Scribe Pro high-accuracy model in minutes during a given billing period.
For example, if you run ten (10) live transcription sessions that are each 30 minutes long using the Scribe Pro model, then 300 total minutes will be used and billed at $0.0067/min (Scribe Pro High-Accuracy) = $2.01 total.
$0.40
$0.0067
Add-ons
Costi aggiuntivi · I componenti aggiuntivi si aggiungono all’API di base e ne richiedono l’utilizzo.
Scribe (Speech-to-text) add-on rates in USD
Add-on
Per hour
About hourly rates
Le tariffe orarie sono calcolate a partire dalle tariffe al minuto e arrotondate al centesimo più vicino per la visualizzazione. La fatturazione si basa sulle tariffe al minuto. Consulta il listino dei crediti per i prezzi attuali al minuto.
Per minute
Diarization
Scribe (Speech-to-text) · Diarization
Scribe API Diarization automatically detects and labels individual speakers in audio recordings for meeting and call analysis. Available as an add-on for Scribe API Batch and Fast modes, and Speech Summarization API.
Description of Metering: Usage is measured based on the total duration of audio processed with speaker identification in minutes during a given billing period. Diarization is an add-on charged in addition to base transcription.
For example, if you batch transcribe ten (10) audio files that are each 30 minutes long with diarization enabled, then 300 total minutes will be used and billed at the combined rate of $0.0025/min (batch transcription) + $0.0008/min (diarization) = $0.99 total.
+$0.05
+$0.0008
Language detection
Scribe (Speech-to-text) · Language detection
Scribe API Language Detection continuously identifies the language being spoken and automatically switches the language used for transcription across available languages. Available as an add-on with Scribe API.
Description of Metering: Usage is measured based on the total duration of audio processed with language detection enabled in minutes during a given billing period. Language Detection is an add-on charged in addition to base transcription.
For example, if you transcribe ten (10) audio files that are each 30 minutes long with language detection enabled, then 300 total minutes will be used and billed at the combined rate of $0.0025/min (batch transcription) + $0.0008/min (language detection) = $0.99 total.
+$0.05
+$0.0008
Text polishing
Scribe (Speech-to-text) · Text polishing
Scribe API Text Polishing refines spoken input into more concise, polished text by removing hesitations, repetitions, and filler words to produce clear, professional output. Available as an add-on with Scribe API.
Description of Metering: Usage is measured based on the total duration of audio processed with text polishing enabled in minutes during a given billing period. Text Polishing is an add-on charged in addition to base transcription.
For example, if you transcribe ten (10) audio files that are each 30 minutes long with text polishing enabled, then 300 total minutes will be used and billed at the combined rate of $0.0025/min (batch transcription) + $0.0017/min (text polishing) = $1.26 total.
Convert text into natural-sounding speech for IVR, notifications, and voice-first experiences.
Measured in 1-character increments.
Base API usage$20.00
Add-on usage$0.00
Estimated monthly total$20.00
List rates in USD, before taxes. Displayed estimates are rounded to the nearest cent and calculated using the listed billing-unit rates. Credits, discounts, and third-party service costs are not included. Questa è solo una stima a scopo illustrativo e gli importi effettivamente fatturati possono variare a causa degli arrotondamenti di fatturazione e delle condizioni dell’account. Refer to the Credit Rate Card for actual pricing.
Text-to-speech rates in USD
Mode
Unit
Price
Standard
Text-to-speech · Standard
TTS API (Fast) converts written text into natural-sounding, human-like speech in seconds with customizable voices, tones, and languages for enhanced accessibility and engaging audio content delivery.
Description of Metering: Usage is measured based on the total number of input characters submitted for speech synthesis during a given billing period.
For example, if you submit ten (10) text inputs that are each 100,000 characters long for Fast synthesis, then 1,000,000 total characters will be used and billed at $20.00/1M characters = $20.00 total.
Build and coordinate conversational AI voice agents that can listen, reason, and respond across your workflows.
Base API usage$1.50
Add-on usage$0.00
Estimated monthly total$1.50
List rates in USD, before taxes. Displayed estimates are rounded to the nearest cent and calculated using per-minute rates. Credits, discounts, and third-party service costs are not included. Questa è solo una stima a scopo illustrativo e gli importi effettivamente fatturati possono variare a causa degli arrotondamenti di fatturazione e delle condizioni dell’account. Consulta il listino dei crediti per i prezzi attuali al minuto.
Voice agent rates in USD
Mode
Per hour
About hourly rates
Le tariffe orarie sono calcolate a partire dalle tariffe al minuto e arrotondate al centesimo più vicino per la visualizzazione. La fatturazione si basa sulle tariffe al minuto. Consulta il listino dei crediti per i prezzi attuali al minuto.
Per minute
Standard
Voice agent · Standard
Voice Agent API enables developers to build and deploy conversational voice agents that understand natural speech, engage in dynamic conversations, and execute tasks through seamless voice interactions.
Description of Metering: Usage is measured based on the total duration of active voice agent sessions in minutes during a given billing period.
For example, if you run ten (10) voice agent sessions that are each 30 minutes long, then 300 total minutes will be used and billed at $0.025/min = $7.50 total.
$1.50
$0.025
Bring your own LLM
Voice agent · Bring your own LLM
Voice Agent - Bring Your Own LLM API enables developers to build and deploy conversational voice agents powered by their own large language model, combining Zoom's voice infrastructure with a custom-integrated LLM to understand natural speech, engage in dynamic conversations, and execute tasks through seamless voice interactions.
Description of Metering: Usage is measured based on the total duration of active voice agent sessions in minutes during a given billing period.
For example, if you run ten (10) BYO LLM voice agent sessions that are each 30 minutes long, then 300 total minutes will be used and billed at $0.018/min = $5.40 total.
Translate text and live speech, and summarize text and audio.
Translator
Traduttore offre traduzioni rapide con un elevato livello di precisione per le conversazioni scritte quotidiane, come i messaggi in chat e le e-mail, affinché la lingua non sia mai un ostacolo.
Base API usage$75.00
Add-on usage$0.00
Estimated monthly total$75.00
List rates in USD, before taxes. Displayed estimates are rounded to the nearest cent and calculated using the listed billing-unit rates. Credits, discounts, and third-party service costs are not included. Questa è solo una stima a scopo illustrativo e gli importi effettivamente fatturati possono variare a causa degli arrotondamenti di fatturazione e delle condizioni dell’account. Refer to the Credit Rate Card for actual pricing.
Translator rates in USD
Mode
Unit
Price
Standard
Translator · Standard
Translator API provides enterprise-grade text translation across multiple languages, enabling developers to deliver multilingual experiences within their applications.
Description of Metering: Usage is measured based on the total number of input characters submitted for translation during a given billing period.
For example, if you submit ten (10) text documents that are each 100,000 characters long for translation, then 1,000,000 total characters will be used and billed at $7.50/1M characters = $7.50 total.
Traduzione da voce a voce tra lingue diverse, affinché i partecipanti possano ascoltare la conversazione nella propria lingua.
Measured in 1-second increments. The $2/hour figure is rounded; estimates use the per-minute rate.
Base API usage$0.03
Add-on usage$0.00
Estimated monthly total$0.03
List rates in USD, before taxes. Displayed estimates are rounded to the nearest cent and calculated using per-minute rates. Credits, discounts, and third-party service costs are not included. Questa è solo una stima a scopo illustrativo e gli importi effettivamente fatturati possono variare a causa degli arrotondamenti di fatturazione e delle condizioni dell’account. Consulta il listino dei crediti per i prezzi attuali al minuto.
Interpreter rates in USD
Mode
Per hour
About hourly rates
Le tariffe orarie sono calcolate a partire dalle tariffe al minuto e arrotondate al centesimo più vicino per la visualizzazione. La fatturazione si basa sulle tariffe al minuto. Consulta il listino dei crediti per i prezzi attuali al minuto.
Per minute
Standard
Interpreter · Standard
STS Interpreter API converts live speech in one language into natural-sounding speech in another language, enabling real-time multilingual voice communication.
Description of Metering: Usage is measured based on the total duration of audio processed in minutes during a given billing period.
For example, if you run ten (10) live interpretation sessions that are each 30 minutes long, then 300 total minutes will be used and billed at $0.0333/min = $9.99 total.
Generate summaries and next steps from transcripts of meetings, phone calls, and other conversations.
Base API usage$4.00
Add-on usage$0.00
Estimated monthly total$4.00
List rates in USD, before taxes. Displayed estimates are rounded to the nearest cent and calculated using the listed billing-unit rates. Credits, discounts, and third-party service costs are not included. Questa è solo una stima a scopo illustrativo e gli importi effettivamente fatturati possono variare a causa degli arrotondamenti di fatturazione e delle condizioni dell’account. Refer to the Credit Rate Card for actual pricing.
Text summarization rates in USD
Mode
Unit
Price
Standard
Text summarization · Standard
Text Summarization API uses AI to condense long-form text into concise summaries with proven accuracy, helping developers surface key insights from transcripts, documents, and other content at scale.
Description of Metering: Usage is measured based on the total number of input characters submitted for summarization during a given billing period.
For example, if you submit ten (10) transcripts that are each 100,000 characters long for summarization, then 1,000,000 total characters will be used and billed at $0.40/1M characters = $0.40 total.
Generate summaries and next steps directly from the audio of meetings, phone calls, and other conversations.
Base API usage$0.23
Add-on usage$0.00
Estimated monthly total$0.23
List rates in USD, before taxes. Displayed estimates are rounded to the nearest cent and calculated using per-minute rates. Credits, discounts, and third-party service costs are not included. Questa è solo una stima a scopo illustrativo e gli importi effettivamente fatturati possono variare a causa degli arrotondamenti di fatturazione e delle condizioni dell’account. Consulta il listino dei crediti per i prezzi attuali al minuto.
Speech summarization rates in USD
Mode
Per hour
About hourly rates
Le tariffe orarie sono calcolate a partire dalle tariffe al minuto e arrotondate al centesimo più vicino per la visualizzazione. La fatturazione si basa sulle tariffe al minuto. Consulta il listino dei crediti per i prezzi attuali al minuto.
Per minute
Fast
Speech summarization · Fast
Speech Summarization API (Fast) turns speech audio into structured summaries and insights within seconds by combining speech-to-text transcription with text summarization in a single API call.
Description of Metering: Usage is measured based on the total duration of audio submitted for summarization in minutes during a given billing period.
For example, if you submit ten (10) audio files that are each 30 minutes long for Fast summarization, then 300 total minutes will be used and billed at $0.0038/min = $1.14 total.
$0.23
$0.0038
Add-ons
Costi aggiuntivi · I componenti aggiuntivi si aggiungono all’API di base e ne richiedono l’utilizzo.
Speech summarization add-on rates in USD
Add-on
Per hour
About hourly rates
Le tariffe orarie sono calcolate a partire dalle tariffe al minuto e arrotondate al centesimo più vicino per la visualizzazione. La fatturazione si basa sulle tariffe al minuto. Consulta il listino dei crediti per i prezzi attuali al minuto.
Per minute
Language understanding
Speech summarization · Language understanding
Language Understanding API filters out sentiment and subjective language from transcripts, delivering more neutral, objective summaries focused on factual content and key information.
Available as an add-on with Speech Summarization API only.
Description of Metering: Usage is measured based on the total duration of audio submitted for language understanding analysis in minutes during a given billing period.
For example, if you submit ten (10) audio files that are each 30 minutes long for analysis, then 300 total minutes will be used and billed at $0.0008/min = $0.24 total.
Search enterprise knowledge and support decisions across your workflows.
Decisions
Valuta testo e immagini per verificare condizioni, scegliere tra opzioni definite o assegnare punteggi secondo una griglia, affinché la tua applicazione possa aiutarti a classificare i contenuti, instradare le richieste e stabilire le priorità del lavoro.
May not be available for all accounts.
Base API usage$0.42
Add-on usage$0.00
Estimated monthly total$0.42
List rates in USD, before taxes. Displayed estimates are rounded to the nearest cent and calculated using the listed billing-unit rates. Credits, discounts, and third-party service costs are not included. Questa è solo una stima a scopo illustrativo e gli importi effettivamente fatturati possono variare a causa degli arrotondamenti di fatturazione e delle condizioni dell’account. Refer to the Credit Rate Card for actual pricing.
Decisions rates in USD
Mode
Unit
Price
Decisions
Decisions · Decisions
The Decisions API provides low-latency, structured inference for intelligent routing, classification, scoring, and agent workflows. Purpose-built for developers who need fast, reliable decision-making at scale, it enables applications to evaluate inputs and return structured outputs in near real-time. May not be available for all accounts.
Description of Metering: Usage is measured based on the total number of tokens used by the Decisions API during a given billing period.
For example, if you submit requests totaling 3,000,000 tokens in a billing period, you will be billed at $0.042/1M tokens = $0.126 total.
per 1M tokens
$0.042
Decisions Pro
Decisions · Decisions Pro
The Decisions Pro API delivers advanced low-latency, structured inference for complex routing, classification, scoring, and agent workflows. Built for developers requiring higher accuracy and deeper reasoning at scale, it evaluates multi-step inputs and returns structured outputs in near real-time. May not be available for all accounts.
Description of Metering: Usage is measured based on the total number of tokens used by the Decisions Pro API during a given billing period.
For example, if you submit requests totaling 3,000,000 tokens in a billing period, you will be billed at $0.10/1M tokens = $0.30 total.
Trasforma le registrazioni delle visite tra pazienti e operatori sanitari in bozze strutturate di note cliniche — sono supportati modelli SOAP, di medicina generale e di salute comportamentale.
Available through Zoom Sales. Designed to help enable HIPAA compliance for customers with a Business Associate Agreement with Zoom. Draft notes require review by a qualified healthcare professional and do not replace clinical judgment.
Base API usage$10.00
Add-on usage$0.00
Estimated monthly total$10.00
List rates in USD, before taxes. Displayed estimates are rounded to the nearest cent and calculated using the listed billing-unit rates. Credits, discounts, and third-party service costs are not included. Questa è solo una stima a scopo illustrativo e gli importi effettivamente fatturati possono variare a causa degli arrotondamenti di fatturazione e delle condizioni dell’account. Refer to the Credit Rate Card for actual pricing.
Clinical Notes rates in USD
Mode
Unit
Price
Standard
Clinical Notes · Standard
Clinical Notes API helps healthcare customers turn recorded or transcribed patient-provider conversations into structured draft clinical documentation, including progress notes and encounter summaries, using medical terminology. Designed to help enable a customer's HIPAA compliance for customers who have entered into a Business Associate Agreement with Zoom. Clinical notes are drafts intended for review by a qualified healthcare professional and are not a substitute for clinical judgment. Available through Zoom Sales.
Description of Metering: Usage is measured based on the total number of clinical notes generated during a given billing period and are billed at $1.00 per note.
For example, if you generate 600 clinical notes, it will be billed at $1.00/note for a total of $600.00.
All prices in USD. Taxes and fees excluded. Usage consumes Zoom Build Platform credits. Credit purchase terms, discounts, and account eligibility depend on your plan. View Zoom Build Platform plans
Start with one endpoint.
Scale to the full stack on the same key and infrastructure.