In App Voice Assistant
For In App Voice Assistant, generated audio sits inside a larger response loop. Network time, model time, first playable audio, playback, and user interruption are separate measurements.
Review current samples, pricing, limits, and documentation before production use.
What this page helps you evaluate
Add speech to an agent while measuring response timing, interruption, and failure behavior.
Conversation loop
Design voice as one part of the agent response path
Return a short response designed for speech.
Deliver audio through the documented API path.
Stop stale audio as soon as a newer turn wins.
Response design
Short replies, clear fallbacks, measurable timing
For In App Voice Assistant, generated audio sits inside a larger response loop. Network time, model time, first playable audio, playback, and user interruption are separate measurements.
Keep spoken responses concise, define a text fallback, and test real turn-taking. A demo that never gets interrupted does not represent a live conversation.
Agent acceptance checks
- Set a target for first playable audio and full completion.
- Define cancel, retry, and text-fallback behavior.
- Avoid reading long URLs or interface chrome.
- Test overlapping turns and slow connections.
Turn length
Write In App Voice Assistant responses for listening and quick interruption. Include the most consequential failure case in the In App Voice Assistant pilot rather than postponing it until after automation. Test In App Voice Assistant with both a typical passage and a deliberately difficult passage so an easy success does not hide edge cases.
State handling
Define what happens when audio starts late, fails, or is superseded. Document any manual cleanup required by In App Voice Assistant; repeated cleanup belongs in the cost and capacity model. Record the script revision, voice, model, reviewer, and decision so the In App Voice Assistant result can be reproduced after a later change.
Observability
Record request, first-chunk, completion, and playback milestones separately. When In App Voice Assistant fails its acceptance check, retain the request metadata and sanitized timing—not sensitive source text—in the incident note. After launch, sample real In App Voice Assistant output regularly and keep user text out of timing or analytics logs unless it is strictly required.
What the product currently documents
Fixed public voice samples are available for review before purchase.
Samples are fixed previews, not a free custom-generation endpoint.
Review sourceCurrent plans, balances, rates, limits, and commercial terms are published on the pricing page.
Pricing can change; use the linked page as the current source.
Review sourceThe current public Pay As You Go plan lists 2 concurrent requests.
Plan limits can change; verify the linked pricing page before deployment.
Review sourceThe documented v3 API supports asynchronous text-to-speech generation and status tracking.
Reviewed 2026-07-24.
Review sourceThe documented WebSocket endpoint streams live raw PCM float32 mono audio at 24 kHz for supported models.
This is an audio-format contract, not a numeric latency claim.
Review sourceQuestions specific to in app voice assistant
What does low latency mean for a voice agent?
Define it precisely—usually time to first playable audio—and report completion time separately.
Should every agent response be spoken?
No. Choose speech when it improves the task and retain accessible visual alternatives.
How should failures sound?
Prefer a concise fallback or text response over repeatedly replaying an old message.
Test In App Voice Assistant with your own acceptance criteria.
Review current samples, pricing, limits, and documentation before production use.