Explore speech-to-text (STT), text-to-speech (TTS) and AI voice agents in 20 languages. Transcribe calls, generate natural speech and help customers in their own language.
Search the catalog or filter it by Voice Agents, text-to-speech and speech-to-text.
20 languages
English
Help customers from the first hello to the next step.
Español
Help customers from the first hello to the next step.
Français
Help customers from the first hello to the next step.
हिन्दी
Help customers from the first hello to the next step.
Deutsch
Help customers from the first hello to the next step.
Italiano
Transcribe conversations. Create natural speech.
Português
Transcribe conversations. Create natural speech.
Nederlands
Turn spoken conversations into useful, accurate text.
Русский
Bring your calls and apps to life with natural speech.
日本語
Bring your calls and apps to life with natural speech.
한국어
Bring your calls and apps to life with natural speech.
ગુજરાતી
Bring your calls and apps to life with natural speech.
తెలుగు
Bring your calls and apps to life with natural speech.
ਪੰਜਾਬੀ
Bring your calls and apps to life with natural speech.
ಕನ್ನಡ
Bring your calls and apps to life with natural speech.
বাংলা
Bring your calls and apps to life with natural speech.
اردو
Bring your calls and apps to life with natural speech.
Kreyòl ayisyen
Help customers from the first hello to the next step.
普通话
Help customers from the first hello to the next step.
العربية
Help customers from the first hello to the next step.
01
Turn customer speech into text for realtime workflows, recorded calls, search, QA and analytics.
02
Generate natural speech for calls, applications, confirmations and automated service experiences.
03
Combine listening, reasoning, business tools and speaking in one realtime customer conversation.
For a searchable call record, start with speech-to-text transcription. For a spoken reminder or application response, choose text-to-speech generation. For an appointment change or a customer-support conversation, explore AI voice agents that can listen, respond and connect to your business tools.
The language cards link to each available product, so you can move from a language to a concrete use case. Search by its English or native name, or choose a product tab to narrow the directory.
A language is the starting point. The voice and delivery should also fit the conversation: a clear appointment reminder, a calm support response or a welcoming introduction. Listen to the voice directory to compare examples, or clone your own voice for generated speech.
Test a short version of your actual workflow with the names, dates and numbers customers will use. Start in the Playground, then connect the selected product to your application.
Speech-to-text (STT) converts spoken audio into written text. Text-to-speech (TTS) converts written text into spoken audio. An AI voice agent combines listening and speaking with conversation logic and business tools to help a caller complete a task.
PyAI speech-to-text covers English, Spanish, French, Hindi, German, Italian, Portuguese, Dutch, Haitian Creole, Mandarin Chinese, Arabic. Use Hear to transcribe conversations for call records, search, customer-service workflows and analysis. Each language’s STT page explains its transcription use cases.
PyAI text-to-speech covers English, Spanish, French, Hindi, German, Italian, Portuguese, Russian, Japanese, Korean, Gujarati, Telugu, Punjabi, Kannada, Bengali, Urdu, Haitian Creole, Mandarin Chinese, Arabic. Use Speak to generate spoken responses, reminders, announcements and application audio from text. Browse the voice directory to hear examples.
The voice-agent directory includes English, Spanish, French, Hindi, German, Haitian Creole, Mandarin Chinese, Arabic. Choose a language’s Voice Agent page to explore customer-support calls, appointment workflows and other conversations that combine speech with business actions.
Start with the language your customers use and the task they need to complete. Choose STT for transcription, TTS for generated speech, or a Voice Agent for a two-way conversation. Then listen to voice samples and test your own names, numbers, appointments and business vocabulary before connecting the workflow.
Yes. The PyAI voice directory links to the voice-cloning flow in the Playground. Create a voice from your own recording, try it with your text, and use it for generated speech. The directory also lets you explore existing voices before choosing one.
Language options are specific to each product. Use the STT, TTS and Voice Agents tabs to see the relevant languages, then follow the product link on a language card. The directory is generated from the same language catalog as the individual product pages.