Quality on the actual call
Evaluate the audio your callers hear, the details the system captures and the action it completes. Native 8 kHz phone audio is available in Omni; use the supported audio format for each product.
PyAI Speak / Cast
Text to speech
Text to speech converts written words into spoken audio. A speech model turns the text into pronunciation, phrasing and a voice waveform that your application can play or stream.
Try the product with your own example
Open the existing product experience, choose the matching settings and evaluate your actual words or recording.
How Text to speech works
Text to speech converts written words into spoken audio. A speech model turns the text into pronunciation, phrasing and a voice waveform that your application can play or stream.
Create clear, natural speech for phone greetings, appointment reminders, accessibility and application responses. Use Speak for low-latency application audio. Choose Cast when a recorded performance needs more direction. A two-way conversation also needs listening, conversation logic and actions.
How PyAI approaches text to speech
A clear integration path
Hear and Speak offer OpenAI-compatible speech endpoints. Omni uses the realtime PyAI SDK. Pair the conversation with AMD, Trace, Recap and managed telephony where your workflow needs them.
Predictable usage billing
Review the product meter, sandbox limits and managed telephony terms on the pricing page. Cloning enrollment and prompt-to-voice design are free; generated speech follows synthesis billing.
Published reference: ~53 ms Speak first audio byte, in-region. Source: Tested, warm-path streaming synthesis; benchmark snapshot 2026-06-24. These are in-region reference measurements, not a language-specific result or latency guarantee. Network, load and deployment affect what you observe. Read the measurement context.
How to use Text to speech with PyAI
- 01
Choose a matching language and voice from the live catalog.
- 02
Send your script to Speak through the OpenAI-compatible speech API.
- 03
Listen to the returned audio, check names and numbers, and connect the output format your application needs.
Voices, accents and your own voice
Listen to stock voices before choosing the voice for your workflow. A language label does not promise every regional accent. For generated speech, you can also enroll a voice you have permission to use or design a voice from a prompt. Verify language and product compatibility before using the result.
Listen to the voice directoryPut it to work
Reception and routing
Greet a caller clearly, understand the request and connect the right next step.
Appointment workflows
Read back names and dates and confirm the actual booking result before announcing success.
Compare on the workflow you need
Comparing PyAI with ElevenLabs? Listen to the same script, then evaluate pronunciation, streaming behavior and the phone-audio format your application needs.
Read the comparison and migration guidanceText to speech FAQ
What is Text to speech?
Text to speech converts written words into spoken audio. A speech model turns the text into pronunciation, phrasing and a voice waveform that your application can play or stream.
When should I use Text to speech?
Use Speak for low-latency application audio. Choose Cast when a recorded performance needs more direction. A two-way conversation also needs listening, conversation logic and actions.
How do I get started with Text to speech?
Choose a matching language and voice from the live catalog. Send your script to Speak through the OpenAI-compatible speech API. Listen to the returned audio, check names and numbers, and connect the output format your application needs.
How much does it cost, and can I test it first?
PyAI offers sandbox testing with limits. Live usage follows the product's billing terms; see https://pyai.com/pricing for current rates, inclusions and managed telephony charges. Free testing does not mean unlimited free production usage.
Can I keep my existing application?
Hear and Speak expose OpenAI-compatible speech APIs. Update your base URL and credentials, select supported language and voice options, and validate the response formats your application uses.
What should I test before using it for customer calls?
Test representative names, dates, amounts, audio conditions and corrections. For agents, include business-tool failures and handoff to a person; inspect the observed outcome, not just a transcript.
Can I use a cloned or designed voice?
Speak supports stock, cloned and prompt-designed voices. Cloning enrollment and voice design are free; synthesis follows the current billing terms. Use a voice you have permission to reproduce and verify its intended language and product compatibility.