Voice and live calls

Understand the three interaction modes#

Text cannot be disabled. Voice-message and real-time toggles control which additional surfaces visitors may use. A saved real-time toggle does not override the workspace's plan entitlement or missing provider configuration.

Configure interaction behavior#

1. Open the site's Agent page and find Voice.
2. Keep Text chat on and choose Voice messages and/or Live real-time voice.
3. If the agent has multiple languages, optionally enable live language mirroring.
4. Set the per-call automatic limit.
5. Select a stock or entitled cloned voice.
6. Save and test each enabled mode separately.

The call limit accepts 30 seconds through 20 minutes in 30-second steps; the default is 3 minutes. It ends an individual call and protects the monthly allowance, but it does not increase the plan's remaining live minutes.

Choose languages and a voice#

Agents can be configured for English, Korean, Uzbek, and Russian. The first language is primary. A single-language agent keeps answering in that language. A multilingual text agent mirrors the visitor when the visitor uses one of the configured languages.

For live calls, language mirroring is an explicit option shown only with two or more languages. When it is off, live calls use the primary language. Uzbek voice is currently best effort because provider speech coverage is less complete; test it with your exact provider and audience before launch.

Stock voices include English-first, multilingual, and Korean-native options. The language label describes the curated delivery, not a hard guarantee. Preview the chosen voice when the dashboard preview control is available, and always test names, abbreviations, currencies, phone numbers, and specialized terminology in the real visitor flow.

Provider keys and fallback#

Voice requires more than a model key:

• Speech-to-text uses a configured transcription provider such as Deepgram or OpenAI.
• Voice messages and connector audio replies need a text-to-speech provider such as ElevenLabs or OpenAI.
• Real-time calls need the configured real-time provider and a plan allowance.
• Voice cloning requires ElevenLabs cloning availability plus a Pro or Studio entitlement.

Configure keys under Settings → AI provider keys and follow Provider keys. A successful text chat proves only the model path; it does not prove transcription, speech synthesis, media upload, or real-time session minting.

Test voice messages#

Use the public hosted site or real embed, not only an owner preview. Grant microphone access, record a short question, and confirm the transcript meaning plus spoken/text response. Then test:

• quiet and noisy environments;
• mobile Safari and Chrome where relevant;
• a long question near the 25 MB public audio cap;
• denied microphone permission;
• unsupported or low-quality audio;
• each configured language.

For embedded sites, the parent CSP and Permissions Policy must allow microphone use. See Security and CSP.

Test live calls#

Confirm the plan has unused live minutes, the site is accessible, and the real-time provider key validates. Begin with a short call, interrupt the agent, switch languages only when mirroring is enabled, and allow the configured call limit to end one test session.

Live minutes are a separate monthly entitlement from normal credits. Issuing the live token charges credits for the server-authorized maximum duration and reserves that duration against the monthly live allowance. Because media flows directly between the browser and provider, a shorter client-reported call cannot be verified and unused time is not partially refunded after token delivery. Server-side token-mint failures are released; abandoned sessions are charged at their authorized limit. End tests cleanly and use the configured call limit when forecasting. See Credits and usage.

Clone a voice responsibly#

Voice cloning is unavailable on Starter. Pro includes one clone; Studio allows multiple under fair use. Re-cloning a site that already has a clone replaces that site's clone rather than consuming another slot.

Use only your own voice or a voice for which you have explicit, documented authorization. The cloning form requires consent and may require typing a site-scoped challenge phrase. A successful clone creates an auditable consent record when the stronger consent gate is enabled.

Upload at least one and at most 10 audio samples. Each file may be at most 10 MB, with a 50 MB combined maximum. Use clean, dry recordings with one speaker, consistent distance, minimal background noise, and representative pronunciation. Do not mix different speakers or heavily processed music.

Cloning reserves and then settles credits. A failed provider call refunds the reservation; a successful clone becomes the agent's selected voice.

Disclosure and safety#

Tell callers they are interacting with AI and synthetic or cloned speech when required by applicable law, provider policy, or user expectations. Do not clone or imitate a person without authorization, use a clone for deceptive identity claims, or collect unnecessary recordings. Define how recordings, transcripts, consent records, and downstream provider data are retained and deleted.

Troubleshooting#

Treat voice as a separate launch surface: text acceptance tests are necessary but not sufficient.