Advanced voice settings

The Advanced settings page controls voice-specific configuration that goes beyond basic voice selection. Open it from the Advanced settings link in the top-right corner of the Voice page. The page has three tabs: Model, Call, and Speech.

​

Model

​

Voice mode

Choose between two architectures for your voice agent:

​

Language model

Select the LLM that powers your voice agent. Recommended for voice: PolyAI’s Raven 3.5 is designed for conversational AI. It produces concise, natural responses without needing example utterances in your prompts — just add raw information and Raven converts it into conversational speech. Raven 3.5 supports 24+ languages, delivers sub-300ms latency, and includes auto-reasoning, out-of-domain detection, and built-in safety. For a full list of available models, see the Model page.

​

Speech recognition

Choose the primary transcription engine and target language for your voice agent.

​

Turn-taking

Control when the agent starts speaking after the caller stops.

​

AI-coustics

---

​

Call

​

Barge-in

Allow callers to interrupt the agent mid-utterance. When enabled, the agent stops speaking as soon as it detects caller speech, shortening VAD time and reducing response latency.

​

How barge-in works

When barge-in is enabled:

1. The agent begins speaking its response.
2. If the caller starts talking, the agent stops its current utterance and begins listening.
3. The agent processes the caller’s input and responds as a new turn.

This also applies to delay control responses – if the caller speaks during a filler phrase, the delay sequence is interrupted.

​

When to use barge-in

Barge-in works well for:

• FAQ-heavy agents where callers may already know what they need
• Long agent responses where the caller wants to redirect the conversation
• Fast interaction styles where responsiveness is a priority

​

When to disable barge-in

Consider disabling barge-in (globally or per flow/step) when:

• The agent is executing a function with external side effects (bookings, payments, form submissions) – the caller may interrupt after the action completes but before hearing the confirmation
• The agent must deliver a mandatory disclosure or disclaimer that cannot be skipped
• The environment is noisy, causing false barge-in triggers from background sounds

​

Per-flow and per-step overrides

You can configure barge-in at a granular level using the experimental JSON config. This lets you enable barge-in globally while disabling it for specific flows or steps where interruption would be problematic. Overrides follow a precedence order: step > flow > global. For example, you can have barge-in off globally, enabled for a specific flow, and disabled again for a sensitive step within that flow.

​

Filler phrases

Configure brief sounds or words the agent uses while processing the user’s input — “One moment…”, “Just a second…”, etc. These fill the gap between the caller finishing and the agent responding, preventing awkward silence.

​

Customer satisfaction survey (CSAT)

When enabled, the agent can route callers into a CSAT survey flow at the end of the conversation. For full configuration details — survey questions, scoring, and dashboard integration — see CSAT surveys.

---

​

Speech

​

Safety filters

Safety filters are configured on a per-channel basis. The voice channel has its own safety filter settings, separate from the chat channel and the project-wide defaults. See Safety filters for the full reference on categories, severity levels, and how filters interact with Guardrails. When safety filters are enabled, adjust the strictness for each category using the sliders: The jailbreak attack filter is always enabled and cannot be turned off.

​

Keyphrases

Keyphrase boosting improves ASR recognition of domain-specific terms like product names, locations, or specialized vocabulary. It biases the ASR model toward recognizing specific words during transcription.

​

Configuring keyphrases

1. Open the Keyphrases section on the Speech tab.
2. Add, edit, or remove keyphrases.
3. Adjust the bias strength for each keyphrase using the slider.
4. Save your changes. Updated keyphrases are applied immediately.

​

Bias strength levels

Maximum bias does not always produce better results. In some cases it can cause the model to misrecognize unrelated words. Start with Default or Boosted and only escalate to Maximum after testing confirms it is needed.

​

Example keyphrases

​

Global vs. per-step vs. dynamic biasing

The Speech tab configures global keyphrase boosting, which applies to every turn of the conversation. Two additional levels of biasing are available for more targeted control:

• Per-step biasing – configure ASR biasing on individual flow steps for contextual precision (e.g. biasing for doctor names only during a name-collection step). See ASR biasing in flows.
• Dynamic biasing from functions – set biasing at runtime using conv.set_asr_biasing() when you need to bias toward values retrieved from an API or database. See ASR biasing from functions.

Precedence rules: When multiple levels of biasing are active, they are merged with the following priority (highest first):

1. Dynamic – biasing set via conv.set_asr_biasing() in functions
2. Per-step – biasing configured on individual flow steps
3. Global – biasing configured on the Speech tab

If the same phrase appears at multiple levels, the highest-priority setting takes precedence.

​

Transcript corrections

Fix common ASR misinterpretations using string matching and regex patterns. Unlike keyphrases, transcript corrections run after the ASR model has produced a transcript – they replace text in the output rather than influencing what the model hears.

​

Configuring transcript corrections

1. Open the Transcript corrections section on the Speech tab.
2. Click Correction to create a new rule.
3. Give the correction a name (must be unique) and optional description.
4. Add one or more regex rules within the correction:
   • Replacement type: Full transcript (replaces the entire transcript if matched exactly) or Partial transcript (replaces only the matching portion).
   • Regex: the regular expression to match the misinterpreted phrase.
   • Replacement: the correct term or phrase (leave empty to delete the matched text).
5. Changes auto-save as you edit.

You can group multiple related regex rules under a single correction. For example, create a correction called “Brand names” containing rules for each brand your agent handles.

​

Example configurations

​

Verifying corrections are applied

1. Open a conversation in Conversation Review.
2. Enable the Transcript corrections layer in Conversation Diagnosis.
3. Check each turn to see whether your correction was triggered.

If a correction is not firing as expected, compare the raw ASR transcript against your regex pattern. Common issues include unexpected whitespace, casing differences, or partial word boundaries.

​

Pronunciation

Control how your agent pronounces specific terms using the International Phonetic Alphabet (IPA) or SSML tags. Useful for brand names, proper nouns, and domain-specific vocabulary that TTS engines frequently mispronounce.

​

How it works

Pronunciation rules use regex patterns to match text in the agent’s response and replace it with IPA notation or SSML markup before it reaches the TTS engine. You can also use SSML such as <break>, <prosody>, and <emphasis> in the replacement string.

​

Multilingual pronunciation rules

For multilingual agents, pronunciation rules are organized by language. Each language has its own set of rules displayed as separate collapsible cards. Rules within a language card only apply to responses in that language. To add a rule for a specific language:

1. Expand the language card.
2. Add the regex pattern and replacement.
3. The rule automatically scopes to that language.

Rules with no language specified apply globally across all languages.

​

Rule evaluation order

Pronunciation rules are evaluated from top to bottom. Each rule runs on the text produced by the rule above it. Because rules are applied sequentially, later rules can modify or override earlier transformations.

​

Common pronunciation patterns

​

Stop keywords

When a response matches a stop keyword pattern, the system halts the response and logs the occurrence. Use stop keywords to catch sensitive content, remove unnecessary preambles, or enforce brand adherence.

​

Stop keyword fields

​

Creating a stop keyword

​

Common use cases

---

​

Diacritics

If your agent operates in a language that uses diacritics – such as č, ć, š, ž, đ – additional configuration is required before keyphrases and transcript corrections will work correctly. Transcript corrections can help with minor post-processing (e.g. fixing Zeljko → Željko) once the correct ASR model is in place, but they are not a substitute for proper language configuration.

​

Environment behavior

Advanced voice settings follow the same branching behavior as other channel settings:

• Make changes in Sandbox for testing
• Promote to Pre-release for UAT
• Deploy to Live for production

​

Related pages