# Retell Tell-1: Voice Model for Live Contact Center Calls

> Source: <https://explainx.ai/blog/retell-tell-1-voice-model-contact-center-latency-2026?utm_source=rss&utm_medium=feed&utm_campaign=blog>
> Published: 2026-11-13 00:00:00+00:00

**Retell on November 12, 2026 launched Tell-1, a language model built for live contact-center phone calls rather than chat windows.** The company describes it as trained on **hundreds of millions of calls**, tuned for **partial answers, detours, and mid-call tools**, with **Tell 1 Beta** priced at **$0.035 per minute** on its [pricing page](https://www.retellai.com/pricing?ref=explainx). The same announcement introduced **Retell Dialer**, an outbound campaign orchestrator for voice and SMS agents.

For builders shipping **phone agents**, the news is a bet that **telephony latency and turn-taking** beat raw benchmark scores from general-purpose chat models.

## TL;DR

| Item | Retell says (Nov 12, 2026) | 
|---|---|
| Model | **Tell-1** voice LM for live calls | 
| Architecture pitch | **Interleaved reasoning** — thinks while speaking | 
| Latency claim | **Under 100 ms** on live bench;**under 300 ms** at peak | 
| Price | **$0.035/min** Tell 1 Beta voice;**$0.011** per chat AI message | 
| Benchmark | **#1 overall** on Retell**vCX** board (vendor-owned) | 
| Companion ship | **Retell Dialer** for outbound campaigns | 

## Why contact centers need a different model shape

Chat-optimized models excel at long context and markdown. A **PSTN caller** punishes anything that sounds like it is reading an essay. Common failure modes Retell names in its [Business Wire release](https://www.businesswire.com/news/home/20261112258243/en/Retell-Launches-Tell-1-a-Language-Model-Built-for-the-Complexity-of-Live-Contact-Center-Calls?ref=explainx) include:

- **Half answers** — caller gives only a first name; the agent must ask for the rest without resetting the form.
- **Detours** — off-topic questions that need acknowledgement before returning to the task.
- **Tool timing** — lookup or booking actions once enough slots are filled, without dead air.

Those are the same stresses covered in explainx.ai guides on [Confucius4 streaming for voice agents](https://explainx.ai/blog/confucius4-r2t2-stable-prefix-streaming-asr-qwen3-voice-agents-2026) and [GPT-Live-style duplex models](https://explainx.ai/blog/openai-gpt-live-transcribe-gpt-transcribe-july-2026), but Tell-1 is Retell’s attempt to **own the default brain** instead of marking up OpenAI or Anthropic per-minute fees.

## Interleaved reasoning on the wire

Retell’s headline mechanism is **interleaved reasoning**: the model updates its internal plan **while audio is already flowing**, rather than waiting for a full completion token batch.

In product terms that means policy exceptions, missing fields, and tool eligibility are tracked **across minutes**, not isolated turns. That mirrors how human reps juggle scripts — and how [decision models](https://explainx.ai/blog/what-are-decision-models-ai-classifiers-guide-2026) gate cheaper classifiers upstream of expensive speech stacks.

## Benchmarks: strong vendor story, independent gap

Retell maintains a public **[vCX benchmark](https://www.retellai.com/changelog/voice-ai-model-benchmark?ref=explainx)** comparing dozens of hosted model configurations. Its November changelog states **Tell-1 ranks #1 overall**, leading **colloquial speech** and **latency**, while other models still win some columns on **grounding** or **tool calling**.

The [best LLM for voice agents](https://www.retellai.com/blog/best-llm-for-voice-ai-agents?ref=explainx) post, updated November 11, 2026, claims **Tell-1 scores 94.45% averaged** across instruction following, grounding, tool calling, and colloquial quality, with **lowest median latency** among **62** listed configs. Those numbers are **Retell-measured**, not third-party.

Compare with adjacent launches:

- [ElevenLabs Scribe v3](https://explainx.ai/blog/elevenlabs-scribe-v3-v3-live-speech-to-text-turn-detection-2026) attacks**ASR and turn detection** , not dialog policy.
- [Fish Audio S2.1 Pro](https://explainx.ai/blog/fish-audio-52m-seed-s2-1-pro-july-2026) chases**TTS quality** for studios.
- **Tell-1** sits in the**dialog + policy** layer Retell already bills per minute.

Retell Tell-1 voice model latency claims for live contact-center phone agents

## Pricing and when Tell-1 beats frontier per-minute models

On the [pricing table](https://www.retellai.com/pricing?ref=explainx), Tell 1 Beta sits at **$0.035/minute**, below many listed frontier entries such as **GPT-6 Astra at $0.32/minute** or **Claude 5.5 Opus at $0.128/minute**. Totals still stack with **voice engine**, **TTS**, telephony, and add-ons like **PII removal** or **safety guardrails**.

For teams already on Retell, switching default LLM to Tell-1 is a **configuration change**, not a migration. For teams comparing platforms, run **your own labeled call set** — vendor boards overweight colloquial speech and latency weights Retell chooses.

## Retell Dialer: outbound orchestration

**[Retell Dialer](https://docs.retellai.com/dialer/overview?ref=explainx)**, launched the same day, connects **outbound lists** to **Tell-1-driven** conversations and downstream SMS nurture agents. Retell emphasizes:

- **Callbacks** at callee-local time instead of blind retries.
- **Qualified handoffs** to human or specialist agents.
- **CRM hooks** with rotation, local presence, and spam monitoring.

That pairs with AWS and telephony trends we track in [Bedrock agent tooling](https://explainx.ai/blog/aws-bedrock-agentcore-runtime-next-generation-november-2026), but Dialer is **Retell-native** campaign glue rather than a generic LLM API.

## How to try Tell-1 this week

1. Open an existing **single-prompt voice agent** on a paid Retell account (flows and multi-prompt agents may still require frontier models — check Retell docs for your agent type).
2. Select **Tell 1 Beta** in the LLM dropdown and keep your prior model as a**shadow** for A/B comparison.
3. Log **median time-to-first-audio-token** ,**tool success rate** , and**human transfer rate** over at least**200 calls** before switching production traffic.
4. If you rely on **OpenRouter-style model fan-out** , remember Tell-1 is**not** an exportable weight — budget stays inside Retell meters.

Retell Tell-1 pricing on the voice agent stack versus frontier models per minute

## vCX benchmark dimensions (how Retell scores voice)

Retell’s public benchmark page breaks “good on a phone call” into columns that chat leaderboards rarely test:

| Dimension | Why it matters on PSTN | 
|---|---|
| **Instruction following** | Sticking to disclosure scripts regulators require | 
| **Grounding** | Citing account facts without inventing balances | 
| **Tool calling** | CRM updates, calendar holds, payment APIs | 
| **Colloquial quality** | Sounding human on low-bitrate audio | 
| **Latency** | Holding barge-in and backchannel timing | 

Tell-1’s claimed **#1 overall** rank is a weighted blend of those columns on Retell infrastructure. If you already run **GPT-6 Luna** or **Gemini 3.5 Flash Lite** on Retell for cost reasons, re-score on **your** compliance script before switching — grounding weights differ by industry.

## Competitive landscape in November 2026

Voice agents sit between **CRM giants** and **model labs**:

- [Salesforce’s Cresta acquisition path](https://explainx.ai/blog/salesforce-cresta-acquisition-voice-agents-service-cloud-2-7-billion-reported-2026) pushes**voice-first service cloud** consolidation.
- [ElevenLabs Scribe v3](https://explainx.ai/blog/elevenlabs-scribe-v3-v3-live-speech-to-text-turn-detection-2026) improves**ears** (ASR + turn detection).
- **Tell-1** tries to own the**brain** on a telephony-native host.

Retell’s bet is vertical integration: **LLM + telephony + orchestration** in one bill, similar to how [AWS Bedrock AgentCore](https://explainx.ai/blog/aws-bedrock-agentcore-runtime-next-generation-november-2026) bundles runtime + governance for text agents.

## Dialer workflows builders can copy

Retell Dialer’s examples in the launch materials map cleanly to agent design patterns:

1. **Requested callback** — parse local time from Tell-1 transcript, write CRM task, suppress duplicate dials.
2. **Qualified lead** — transfer to human or high-tier agent with**context bundle** (Retell conversation id).
3. **Nurture path** — trigger SMS agent with**shorter** Tell-1 or chat pricing ($0.011/msg).

If you orchestrate multi-agent flows, mirror that split: **cheap text decision model** for SMS, **Tell-1** for voice, echoing [decision-model routing guides](https://explainx.ai/blog/llm-vs-clm-vs-decision-models-which-to-use-2026).

## Stack economics: voice engine + LLM + telephony

Retell invoices in **layers**. Tell-1’s **$0.035/min** is only the LLM row. Production calls also incur:

- **Retell Voice Infra** at**$0.055/min** on the pricing page
- **TTS** choices from**$0.015** to**$0.10/min** depending on ElevenLabs tier
- **Telephony** around**$0.015/min** for U.S. Twilio routes
- Optional **PII removal** ,**safety guardrails** , and**QA** surcharges

A back-of-envelope minute can exceed **$0.12** before carrier taxes. That is still often below stacking **GPT-6 Astra** voice pricing on the same table, but not automatically cheaper than **Gemini 3.5 Flash Lite** at **$0.0096/min** LLM if your script tolerates weaker grounding.

Finance teams should model **cost per completed task**, not cost per minute — the same lesson from [Bedrock cost-per-task baselines](https://explainx.ai/blog/aws-bedrock-cost-per-task-not-per-token-agent-roi-baselines-holdouts-part-2-2026).

## Compliance and enterprise knobs

Retell’s enterprise plan advertises **SSO**, **RBAC**, **custom MSA/DPA**, and **high concurrent call caps**. For regulated callers (health, finance), pair Tell-1 with:

- Recorded consent flows required in your jurisdiction
- **Knowledge base** add-on (+$0.005/min) when answers must cite uploaded policy PDFs
- Human **transfer** targets when confidence drops — measure how often Tell-1 requests handoff versus frontier models

Those operational metrics usually matter more to legal review than a **94.45%** vendor benchmark average.

## Build checklist before production cutover

1. Record **baseline** median latency and**transfer rate** on your incumbent LLM for one week.
2. Enable Tell-1 on **10%** traffic with**recording consent** flags unchanged.
3. Compare **tool error rate** on your top three API tools (payments, account lookup, scheduling).
4. Reconcile **per-minute invoice** including voice engine + TTS + telephony surcharges.
5. Document rollback — keep previous model id in config for instant revert.

## Limits and open questions

- **No open weights** — you cannot benchmark Tell-1 on-premises beside[pplx-decider](https://explainx.ai/blog/perplexity-pplx-decider-v1-3-locate-extraction-november-2026) or[Sarvam Prism](https://explainx.ai/blog/sarvam-prism-open-weights-decision-model-105b-44ms-calibrated-confidence-apache-2-2026) .
- **Benchmark ownership** — vCX is maintained by the vendor whose model now ranks first.
- **Duplex stacks** — Retell’s own[GPT-Live-1 changelog](https://www.retellai.com/changelog/gpt-live-1?ref=explainx) still serves callers who want**OpenAI full-duplex voice** with a separate text planner; Tell-1 is a different architecture choice.

## Related reading

## When to keep a frontier model on voice

Keep **Claude 5 Sonnet** or **GPT-6 Sol** on Retell when your agent must cite **long uploaded policies** beyond Tell-1’s training distribution, when you need **multilingual** coverage Retell has not published for Tell-1, or when legal insists on a **named foundation-model vendor** in contracts. Tell-1 is a bet that **phone-native finetuning** beats general reasoning on median calls — not that frontier models lose on every row of the vCX board.

*Pricing and benchmark claims reflect Retell’s public pages as of November 13, 2026. Confirm rates on retellai.com before budgeting.*