Skip navigation
Introducing Tell-1, Retell’s LLM purpose-built for contact centers.
0:00 / 3:03

Introducing Tell-1, Retell’s LLM purpose-built for contact centers.

Retell AI

@retellai4K followers

Visit on X
242 likesDownloadOriginal post

72,242 views

Introducing Tell-1, Retell’s LLM purpose-built for contact centers. Intelligence. Latency. Cost. We built Tell-1 to deliver all three. Tell-1 uses interleaved reasoning: it answers first and reasons while it speaks, following complex business rules, choosing the right next action, and handling unexpected turns while keeping the conversation moving. Benchmarks & technical breakdown below.

26 Comments

Comments from the original post on X (Twitter)

  • Retell AI's profile picture

    @retellai

    Tell-1 by the numbers: → 94.4% average score on Retell’s vCX benchmark (#1 overall) → ~150ms time to first token → $0.035 per minute Explore the full results and methodology:

    10 likes

  • Retell AI's profile picture

    @retellai

    Tell-1 has also been evaluated by independent testing firms including @cekuraAi , @covaldev, @getbluejay_ai and @HammingAI . Explore their results: → Cekura: → Coval: → Bluejay: → Hamming AI:

    12 likes

  • Retell AI's profile picture

    @retellai

    What happens while Tell-1 is speaking? As its first sentence plays, it reasons about which business rule applies, what information is missing, and whether to call a tool. Go deeper into the training, inference, and evaluation behind Tell-1:

    8 likes

  • Retell AI's profile picture

    @retellai

    Tell-1 is live on Retell. Try it on your own calls - with your business rules, workflows, and the unexpected turns your customers bring. We’d love to hear what you think.

    6 likes

  • erkamkavak's profile picture

    @KavakErkam

    @zexiazh Is it going to be available as API?

    1 like

  • Brutal Lee's profile picture

    @brutallee666

    @zexiazh This model is blazingly fast

    1 like

  • Shanay Gaitonde's profile picture

    @shanaygaitonde

    @zexiazh what happens when the reasoning catches that the first answer was wrong

    1 like

  • Vito Botta's profile picture

    @vitobotta

    @zexiazh Answering first and reasoning while it talks is a clever latency trick. What happens when it realises it's wrong mid-sentence?

    1 like

  • Toma Rares's profile picture

    @rarestomaa

    @zexiazh what happens when the reasoning disagrees with what it already said out loud?

    1 like

  • Aditya's profile picture

    @I_Aditya_

    @zexiazh Excited to give it a shot 🚀

  • Chole Syntax Expert AI's profile picture

    @CholeSyntax

    @zexiazh Answer first reason while speaking that's exactly how real contact centers should feel

  • 波若波罗蜜's profile picture

    @YXxquf

    @zexiazh Reasoning while speaking makes interruptions especially interesting: the customer can change the request before the thought finishes. Does your benchmark test whether Tell-1 cancels an outdated tool action after a mid-sentence correction?

  • Abdulrahman khalifa's profile picture

    @Abdulrahman_NK_

    @zexiazh Answering first and reasoning while speaking is a smart fix for voice latency. In a contact center a 2 second pause feels like forever.

  • Signal Forge's profile picture

    @Dinamo51648539

    @zexiazh Your technical note says the lead bonus trades latency for accuracy. I'd score the opening sentence separately: premature promises on refunds, bookings or identity checks before the rule or tool result arrives. A correction in sentence two doesn't undo what the caller heard.

  • eStomes's profile picture

    @eStomes

    @zexiazh Very impressive initial tests. Congrats.

  • Grumpy's profile picture

    @Grumpysmurf_xyz

    @zexiazh exactly how skilled operators talk

  • Jerry Liu's profile picture

    @tfmlab

    @zexiazh Answer-first, reason-while-speaking commits spoken words before reasoning finishes. Worth reporting how often later reasoning contradicts what was already said, and how the agent repairs it mid-turn, next to time-to-first-audio. Latency gains matter less if corrections rise.

  • Ella Tech & Tool's profile picture

    @EllaTech0

    @zexiazh This is so true smart speed changes contact centers completely

  • Shivam Gupta's profile picture

    @ShivamGuptaim

    @zexiazh The first sentence needs to stay honest while the reasoning catches up. “Let me check whether that qualifies” buys time; “yes, we can refund that” creates a promise. I’d test premature commitments explicitly, not just whether the eventual tool call was correct.

  • Baran Ai | tools & updates's profile picture

    @BaranwithAi

    @zexiazh Answering first then reasoning while speaking is clever design