Description

️ Tool Name: 🖼

Inworld Realtime TTS

Categories: 🔖

Audio, Speech, and Music
Integrations and APIs
Text-to-Speech / Speech-to-Text
Voice Cloning

️ What does this tool offer? ✏

Inworld Realtime TTS is Inworld’s real-time text-to-speech technology, providing voice models tailored for applications that require fast, realistic, and interactive speech generation. The platform includes Realtime TTS-2, the current flagship model, and Realtime TTS-2 Flash, designed for applications requiring low latency and lower cost, in addition to previous Realtime TTS models such as Realtime TTS 1 and Realtime TTS 1-Max. Realtime TTS-2 offers advanced vocal expression and the ability to control delivery style using natural language instructions; it also supports nonverbal cues such as laughter, sighs, breathing, coughing, yawning, and throat-clearing, and a single voice can be used across multiple languages. The platform offers instant voice cloning using a short voice sample, as well as Voice Design for creating custom voices, and supports control over speech rate, pitch, custom pronunciation, timestamps, and alignment data. Realtime TTS-2 offers a latency of less than 100 ms based on server-side TTFB measurements, while Realtime TTS-2 Flash achieves 25 ms, according to the official website. The current models also support more than 200 languages with multilingual capabilities and the ability to switch between languages using BCP-47 codes.

Realtime TTS can be used via the API and Realtime API, and you can try out the voices and features directly through the TTS Playground. Inworld provides integration interfaces for real-time voice applications, including WebSocket, with WebRTC and SIP support in early access, according to the official website. The technology can be used in applications including voice agents, consumer apps, educational apps, games, virtual companions, and other applications that require interactive real-time voice.

Realtime TTS 1, announced by Inworld in 2025, provided realistic, context-aware voice synthesis and voice cloning from short samples without prior training, and was available via API and TTS Playground, while Realtime TTS 1-Max was available in beta. Currently, Inworld offers Realtime TTS-2 as its flagship model, with Realtime TTS-2 Flash as a faster option focused on reducing latency and cost.

Inworld also provides developer tools, including an API Reference, Documentation, and TTS Playground, as well as an open-source training framework linked to Realtime TTS research, allowing developers to rebuild TTS models according to the methodology published by the company. The platform also offers integration capabilities with voice application systems, and its models can be used directly through APIs.

What does it actually offer based on user experience? ⭐

• It provides fast speech synthesis suitable for applications that require immediate response, with a TTFB of less than 100 ms in Realtime TTS-2 and 25 ms in Realtime TTS-2 Flash, according to measurements published by Inworld.

• Realtime TTS-2 offers advanced voice expression with the ability to control tone and emotions using natural language instructions directly within the text.

• It allows for the addition of nonverbal cues such as laughter, sighs, breathing, coughing, yawning, and throat clearing to the generated speech.

• It enables instant voice cloning using a short voice sample; Inworld notes that voice cloning can be performed using a clean sample from a single speaker lasting 5 to 15 seconds.

• Voice Design allows you to create a custom voice from a written description, without the need for a reference audio sample.

• It supports multilingual use; the current website states that it supports over 200 languages, with the ability to use a single voice across multiple languages.

• According to Inworld, the quality of Realtime TTS is evaluated through blind listening tests involving thousands of users, The company also notes that Realtime TTS-2 has been fine-tuned to achieve greater expressiveness while reducing issues such as hallucination and word dropouts and improving conversational naturalness. These are published results and descriptions from Inworld and do not constitute an independent evaluation by me.

• The platform allows you to test voices directly through the TTS Playground before integrating them into apps, then transition to the API once you begin development.

Does it include automation? 🤖

The officially available information does not mention a standalone automation system within Realtime TTS in the traditional sense of task automation tools. However, the tool provides an API and a Realtime API, allowing developers to integrate speech synthesis into their applications and automate programming workflows. The Realtime API also allows you to run speech layers, text-to-speech, and other features within a single session, with the option to use WebSocket, while WebRTC and SIP are available in early access.

Pricing Model: 💰

Freemium / Paid / Subscription / Pay-as-you-go. Inworld offers an On-Demand plan that you can start for free, as well as monthly subscription plans—including Creator, Builder, Developer, and Growth—in addition to a custom-priced Enterprise plan. The cost per character decreases at higher tiers, and the company offers an annual payment option with two free months. TTS usage is billed by character count, STT is billed by the hour, and LLM models are billed based on the provider’s rates.

🆓 Free Plan Details:

ItemDetails
PlanOn-Demand
PriceStart for free
TTS-2$25 per 1 million characters
TTS-2 Flash$15 per 1 million characters
STT 1$0.15 per hour
LLMsAt cost
Included TTSUp to 70 minutes
Custom voices100
Voice cloning and voice designAvailable
Real-time APIAvailable
LLM Models via RouterOver 220 models
Commercial LicenseAvailable
SupportCommunity support
AccessOn-Demand can be selected from the billing page

The pricing page notes that On-Demand is suitable for evaluation and prototyping, and that it provides up to 70 minutes of TTS for free. The official cost calculator also shows that the recommended plan when selecting Text-to-Speech with 0 minutes of usage is On-Demand, and the total cost of the plan is Free.

Paid plan details: 💳

PlanMonthly PriceRealtime TTS-2Realtime TTS-2 FlashMonthly CreditKey Features
Creator$25/mo$20 per 1M characters$10 per 1M characters$25Up to 33% off, 500 custom voices, 40K characters per request in TTS Playground, and the ability to create and share Workspaces and manage your team
Builder$100/mo$17.50 per 1M characters$9 per 1M characters$100Up to 40% off, 3,000 custom voices, higher synchronization limits, and the ability to create and share Workspaces and manage your team
Developer$300/mo$15 per 1M characters$8 per 1M characters$300Up to 47% off, 10,000 custom voices, higher synchronization limits, professional voice cloning as an add-on, and priority email support
Growth$1,500/mo$12.50 per 1M characters$7 per 1M characters$1,500Up to 53% off, 30,000 custom voices, higher API limits, one professional voice cloning, and ZDR, HIPAA, and BAA add-ons
EnterpriseCustomStarting at $5 per 1M charactersLess than $5 per 1M charactersCustomCustom pricing and limits, price match, SLA and DPA, data residency in the EU and India, and a dedicated account manager and Slack channel

The official pricing page shows that TTS-2 prices range from $25 per million characters for On-Demand to $20 for Creator, $17.50 for Builder, $15 in Developer, $12.50 in Growth, and as low as $5 in Enterprise. As for TTS-2 Flash, prices start at $15 and go down to $10, $9, $8, and $7, respectively, and then to less than $5 in the Enterprise tier. Additional usage is billed at the same rate as the plan.

FeatureOn-DemandCreatorBuilderDeveloperGrowthEnterprise
API AccessAvailableAvailableAvailableAvailableAvailableAvailable
Audio downloadsAvailableAvailableAvailableAvailableAvailableAvailable
Character limit in TTS Playground2,00040,00040,00040,00040,000Custom
Custom voices1005003,00010,00030,000Custom
Instant voice cloningAvailableAvailableAvailableAvailableAvailableAvailable
Professional voice cloning———Add-on1Custom
Voice designAvailableAvailableAvailableAvailableAvailableAvailable
SteeringAvailableAvailableAvailableAvailableAvailableAvailable
Speaking rate controlAvailableAvailableAvailableAvailableAvailableAvailable
Temperature controlAvailableAvailableAvailableAvailableAvailableAvailable
200+ languagesAvailableAvailableAvailableAvailableAvailableAvailable
Custom pronunciationAvailableAvailableAvailableAvailableAvailableAvailable
TimestampsAvailableAvailableAvailableAvailableAvailableAvailable
Concurrent requests51050150500Custom
Estimated concurrent user sessions20402006002,000Custom
GDPR & SOC 2 Type IIAvailableAvailableAvailableAvailableAvailableAvailable
Commercial licenseAvailableAvailableAvailableAvailableAvailableAvailable
Credit rolloverAvailableAvailableAvailableAvailableAvailableAvailable
HIPAA & BAA————Add-onAvailable
Zero data retention————Add-onAvailable
SLA & DPA—————Available
Data residency—————EU, India
Payment—Credit cardCredit cardCredit cardCredit cardInvoicing / PO
SupportCommunityCommunityCommunityPriority EmailPriority emailAM + Slack

The official pricing page explains that the estimated number of concurrent user sessions varies depending on usage, but is typically at least four times the concurrent request limit. It also explains that paid credits are subject to specific expiration terms, and that rollover or cancellation details depend on the subscription status and billing cycle.

How to access the tool: 🧭

Access MethodDetails
WebYou can visit the official Inworld website and try the service via TTS Playground
TTS PlaygroundTry out the voices, settings, and voice synthesis right away
APIIntegrate Realtime TTS into your applications via the API
Realtime APIBuild real-time voice applications and run voice layers and models within a single session
WebSocketAvailable in the Realtime API
WebRTCAvailable in Early Access
SIPAvailable in Early Access
DocumentationDocumentation and API Reference are available to developers
Enterprise PlansContact the sales team for pricing and custom limits

Inworld offers the ability to try out Realtime TTS through the TTS Playground. You can also create an API key and start making API requests. According to the official website, the service currently supports audio outputs including MP3, Linear PCM/WAV, and Opus.

Demo link or official website: 🔗

Inworld Realtime TTS – Official Website

TTS Playground – Try the tool now

Official Pricing Page

Official API Documentation

Pricing Details

Realtime TTS-2 is the #1 model on Artificial Analysis and the fastest TTS in the world in its class. Inworld offers pricing that scales with user needs; you can choose a plan and receive monthly credits to use across TTS, STT, and LLMs. Higher tiers provide volume discounts, additional features, higher limits, and more, with Monthly and Yearly options · 2 months free. The On-Demand plan, designed for evaluation and prototyping, includes a free starter option; TTS-2 is priced at $25/1M characters, and TTS-2 Flash at $15/1M characters, STT 1 is priced at $0.15/hr, while LLMs are billed at cost. The plan includes up to 70 min of TTS, 100 custom voices, voice cloning and voice design, real-time API access, 220+ LLM models via Router, a commercial license, and community support. It can be selected via “Choose On-Demand” at https://platform.inworld.ai/billing. The Creator plan, designed for content creation and small projects, costs $25/mo. The price for TTS-2 is $25/$20 per 1M characters, and the price for TTS-2 Flash is $15/$10 per 1M characters, STT 1 is priced at $0.15–$0.10/hr, while LLMs are billed at cost. It includes $25 in credits per month, up to 33% off TTS & STT rates, 500 custom voices, 40K chars per TTS Playground request, workspace creation and sharing, team management, and everything in On-Demand. You can select a plan through “Choose Creator” at https://platform.inworld.ai/billing. The Builder plan, designed for growing projects and small teams, costs $100/mo. The price for TTS-2 is $25–$17.50/1M chars, and the price for TTS-2 Flash is $15–$9/1M chars, STT 1 is priced at $0.15–$0.10/hr, while LLMs are billed at cost. It includes $100 in credits per month, up to 40% off TTS & STT rates, 3,000 custom voices, increased concurrency limits, workspace creation and sharing, team management, and everything included in the Creator plan. You can select this plan via “Choose Builder” at https://platform.inworld.ai/billing. The Developer plan, designed for production applications, costs $300/mo; the price for TTS-2 is $25–$15/1M chars, and the price for TTS-2 Flash is $15–$8/1M chars, STT 1 is priced at $0.15–$0.10/hr, while LLMs are billed at cost. It includes $300 in credits per month, up to 47% off TTS & STT rates, 10,000 custom voices, increased concurrency limits, Professional voice cloning (add-on), and priority email support, in addition to everything in Builder. It can be selected via “Choose Developer” at https://platform.inworld.ai/billing. The Growth plan, designed for large-scale deployments and compliance, is priced at $1,500/mo; TTS-2 is priced at $25/$12.50 per 1M characters, and TTS-2 Flash is priced at $15/$7 per 1M characters, STT 1 is priced at $0.15–$0.10/hr, while LLMs are billed at cost. It includes $1,500 in credits per month, up to 53% off TTS & STT rates, 30,000 custom voices, higher API concurrency and limits, 1 professional voice clone, ZDR, HIPAA, and BAA (add-ons), in addition to everything included in the Developer plan. It can be selected through “Choose Growth” at https://platform.inworld.ai/billing. The Enterprise plan offers custom pricing, limits, and terms at a custom rate, with TTS-2 pricing as low as $5/1M, TTS-2 Flash pricing under $5/1M, STT is priced at 1 Custom, and LLMs are priced at Custom. You can contact sales via https://inworld.ai/contact-sales. The plan includes price match available, custom limits, SLA & DPA, EU & India data residency, a dedicated Account Manager & Slack channel, in addition to everything in the Growth plan. There is also an “Estimate your monthly cost” option that allows you to select the desired products and features and your expected usage to find the right plan, with Monthly and Yearly options · 2 months free. Step 1 is “Select product or feature,” followed by “Text-to-Speech.” Step 2 is “Minutes of audio per month,” where the value shown is 0 min with a range of 0 to 100K+. The “Recommended plan” is “On-Demand,” and the “Plan cost” and “Total” are both “Free.” You can select “Choose On-Demand” via “https://platform.inworld.ai/billing.” The estimate is based on Realtime TTS-2 Flash rates; the actual cost may be higher with Realtime TTS-2, while LLMs are billed separately at the provider’s cost. In the “Compare plans” section, you can filter plans by product to view pricing, limits, and features for each tier. Products include Text-to-Speech, Speech-to-Text, Realtime API, and LLM Router, with Monthly and Yearly options · 2 months free. The On-Demand plans include Start (free), Creator ($25/mo), Builder ($100/mo), Developer ($300/mo), Growth ($1,500/mo), and Enterprise (Custom). In the “Pricing per 1M characters/per minute” section, assuming that one minute of audio is ~1,000 characters, the price for Realtime TTS-2 in the plans is, in order, $25, $20, $17.50, $15, and $12.50 and as low as $5, while the price for Realtime TTS-2 Flash is $15, $10, $9, $8, $7, and under $5; overage usage is billed at the same rate as your plan. Features include API access on all plans and audio downloads on all plans. Character limits in TTS Playground are 2,000 for On-Demand, 40,000 for Creator, 40,000 for Builder, 40,000 for Developer, 40,000 in Growth, and Custom in Enterprise. The number of custom voices is 100, 500, 3,000, 10,000, 30,000, and Custom, respectively. Instant voice cloning is available on all plans, while Professional voice cloning — in On-Demand, — in Creator, — in Builder, as an add-on in Developer, 1 in Growth, and Custom in Enterprise, Voice design, Steering (Realtime TTS-2 only), Speaking rate control, Temperature control, 200+ languages, Custom pronunciation, and Timestamps are available on all plans, while New workspace creation is available in On-Demand — Creator — Builder — Developer — Growth — and Enterprise Custom, and Workspace sharing is available in On-Demand — Creator — Builder, Developer, Growth, and Enterprise Custom. Limits include the number of concurrent requests, which are 5, 10, 50, 150, 500, and Custom, respectively, while the estimated concurrent user sessions are 20, 40, 200, 600, 2,000, and Custom. Note that the number of concurrent user sessions that can be handled will vary by use case, but is typically at least 4x your concurrent request limit. Platform & Compliance includes API access, GDPR & SOC 2 Type II, a commercial license, and credit rollover across all plans, while HIPAA & BAA — in On-Demand, — in Creator, — in Builder, — in Developer, and as an add-on in Growth, and are available in Enterprise; Zero data retention — is included in On-Demand, Creator, Builder, and Developer, is an add-on in Growth, and is available in Enterprise; SLA & DPA — are included in all plans up to Growth and are available in Enterprise; and Data residency — is included in all plans up to Growth, while EU and India options are available in Enterprise. As for Payment, it is — in On-Demand; Credit Card in Creator; Credit Card in Builder; Credit Card in Developer; Credit Card in Growth; and Invoicing / PO in Enterprise. Support is Community in On-Demand; Community in Creator; Community for Builder, Priority Email for Developer, Priority Email for Growth, and Account Manager + Slack for Enterprise. You can select On-Demand, Creator, Builder, Developer, or Growth via https://platform.inworld.ai/billing, while you can contact Enterprise via https://inworld.ai/contact-sales. The FAQs include questions such as “What are credits and how do they work?”, “Do unused credits roll over?”, “What happens if I go over my credits?”, “What happens when I upgrade, downgrade, or cancel my subscription?”, and “What plan is right for me?” The “Start building” section is available with the “Get Started Free” option at https://platform.inworld.ai/billing and the “Contact Sales” option at https://inworld.ai/contact-sales. Products include Realtime TTS at https://inworld.ai/tts, Realtime Router at https://inworld.ai/router, Realtime STT at https://inworld.ai/speech-to-text, Realtime API at https://inworld.ai/realtime-api, and Models at https://inworld.ai/models. The “Solutions” category includes Social & Companions at https://inworld.ai/social-companions, Learning & Education at https://inworld.ai/learning-education, Health & Wellness at https://inworld.ai/health-wellness, Agentic Workforce at https://inworld.ai/agentic-workforce, and Games & Media at https://inworld.ai/gaming-media. The Developers section includes Documentation at https://docs.inworld.ai/docs/introduction, API Reference at https://docs.inworld.ai/api-reference/introduction, and Playground at https://platform.inworld.ai/tts-playground; Socials includes X at https://x.com/inworld, LinkedIn at https://www.linkedin.com/company/inworld-ai, and GitHub at https://github.com/inworld-ai; “Company” includes “Careers” at https://inworld.ai/careers, Blog at https://inworld.ai/blog, Security at https://inworld.ai/security, Resources at https://inworld.ai/resources, and Support at https://docs.inworld.ai/portal/support. The copyright notice appears at © 2021–2026 Inworld AI, and includes Privacy at https://inworld.ai/privacy, Terms at https://inworld.ai/terms, and Model Provider Terms at https://inworld.ai/legal/model-providers. The text "Pricing that scales with you" appears at the bottom of the page.