TelEcho

What it does

Done-for-you service

PartlyYou run the software yourself in a no-code builder, but the vendor also sells hands-on help: strategy calls, an onboarding meeting and prompt-engineering support appear only in the Enterprise column of the comparison table.Work with us to design, launch, and scale production-ready AI-powered voice assistants.telecho.io/pricing ↗

How much it does unattended

Runs autonomously

YesAgents run whole calls and write to connected systems without a person on each interaction; escalation rules and human handoff conditions are set during agent setup rather than removed.They can update CRMs, schedule appointments, trigger workflows, and route calls without needing a human on every interaction.telecho.io/pricing ↗

Agent permissions

YesScope is bounded at setup rather than per action: guardrails, escalation and handoff conditions, business hours and response policies are configured before an agent goes live, and no per-step approval prompt is described.Escalation rules and human handoff conditionstelecho.io/how-it-works ↗

Not established: Multi-agent

Which models it runs on

Claude

PartlyClaude appears as a place you drive TelEcho from, via the vendor's MCP integration, not as a model the agent can run on; the pricing calculator's LLM selector offers OpenAI models only.Define and configure your agent directly from ChatGPT or Claude via TelEcho's native MCP integration, without switching platforms.telecho.io/how-it-works ↗

GPT

YesGPT is the platform's reasoning layer: the pricing calculator meters GPT-5, GPT-5 Mini, GPT-5 Nano, GPT 4.1 and GPT 4.1 Mini, and OpenAI is the sole LLM provider named in the sub-processor table.OpenAI LLM reasoning and response generation Call transcripts, workflow context United Statestelecho.io/security ↗

Open models

NoNo open-weight option is offered anywhere: the calculator's five LLM choices are all OpenAI, and the vendor's complete sub-processor inventory names OpenAI as the only LLM provider that touches customer data.TelEcho engages the following Sub-processors to provide the Service.telecho.io/security ↗

Model choice

PartlyYou choose the telephony carrier, the STT engine, the TTS voice and the execution pipeline, but every LLM option in the calculator comes from one vendor, so model choice stops at OpenAI.We support multiple conversational execution models, depending on latency, compliance, and use case.telecho.io/features ↗

Where you use it

In a browser

YesThe whole product is a hosted web application: a visual drag-and-drop workflow builder, live dashboards, session replay and versioning, with nothing to install locally.TelEcho's visual workflow builder makes conversational AI design fast and precisetelecho.io/how-it-works ↗

Not established: On the command line

Whose machine it runs on

Open source

NoThe platform is closed and proprietary: the terms forbid decompiling or extracting source, ownership of the Services stays with RTC LEAGUE, and only bundled third-party open-source components are acknowledged.Reverse engineer, decompile, or attempt to extract source code or the underlying AI modelstelecho.io/legal/terms ↗

Not established: Self-hosted

What it costs to run

How it meters

YesBilling follows conversation time, not seats: a platform base fee of $0.08 per minute plus metered telephony, LLM, STT and TTS, with WhatsApp and WeChat messages priced per message.Transparent pricing = Platform plan + Usage. Use the calculator to estimate your monthly spend.telecho.io/pricing ↗

Free tier

PartlyA free Build tier exists for evaluation with one agent deployment and basic observability, and Pay-as-you-go includes twenty concurrent calls, but no free minute allowance is published so real calls still meter per minute.free 20 calls, can purchasetelecho.io/pricing ↗

API access

PartlyA Voice Agent API exists and carries an uptime commitment, and webhooks, custom REST integration and Enterprise metrics-export APIs are advertised, but the site publishes no endpoint reference, no docs route and no key-issuing flow.Voice Agent API & Telephony Routingtelecho.io/security ↗

MCP server

YesTelEcho documents a native MCP integration letting an agent inside ChatGPT or Claude define and configure TelEcho agents; no server address, tool inventory or auth flow is published to verify scope.Define and configure your agent directly from ChatGPT or Claude via TelEcho's native MCP integration, without switching platforms.telecho.io/how-it-works ↗

Bring your own key

PartlyYou may bring your own carrier by routing calls over third-party SIP and you choose the cloud region your data sits in, but nothing offers your own OpenAI, STT or TTS keys, so inference runs on TelEcho's provider accounts.Third-party SIP $0.004/mintelecho.io/pricing ↗

Buying it for a team

A company can buy it

YesThis is sold to companies: an Enterprise plan goes through sales, and MSA, DPA, SLA, BAA and a completed vendor risk questionnaire are offered to Enterprise customers under NDA.If you are using the Services on behalf of an organization, you represent that you have the authority to bind that organization.telecho.io/legal/terms ↗

Seat model

NoNothing is priced per seat: users are invited into one account and charges follow minutes, so there is no published per-user fee, no seat floor and no seat ceiling, only 'limited team access' on Build.You may invite additional users to access your account.telecho.io/legal/terms ↗

Admin controls

PartlyEvery agent is constrained at setup by guardrails and escalation rules, but the administrative controls that decide who may change them - RBAC, region pinning, retention controls - are listed as Enterprise-plan lines.TelEcho offers enterprise-grade controls so your AI voice agent deployments remain secure, auditable, and compliant.telecho.io/features ↗

Audit log

PartlyAudit trails are documented for TelEcho staff access to customer data, and calls carry session replay and transcripts, but no customer-visible log of administrative or configuration changes is described.Centralized logging and intrusion detection across the API, telephony, and application layers, with audit trails for any access to Customer Datatelecho.io/security ↗

Single sign-on

PartlySingle sign-on with MFA is confined to Enterprise-tier accounts, neither SAML nor OIDC is named as the protocol, and the pricing page hedges the same capability as 'SSO/SAML (if supported)'.Single sign-on (SSO) and multi-factor authentication (MFA) available for Enterprise-tier Customer accounts, and enforced internally for…telecho.io/security ↗

Not established: Pooled budget

What happens to your code

Opt out of training

PartlyThe opt-out is one TelEcho sets on your behalf rather than a switch you control, and it binds only where each model provider offers one; TelEcho separately promises not to train its own models on identifiable content.We configure these integrations, where offered by the provider, to disable use of Customer-submitted data for training the provider's general-purpose…telecho.io/legal/privacy-policy ↗

Data residency

PartlyYou select the cloud region that stores your data and Enterprise adds region pinning, yet every named telephony, speech and LLM sub-processor processes in the United States, with EU transfers covered by standard contractual clauses.Encrypted, redundant backups across availability zones for the cloud region selected by the Customertelecho.io/security ↗

Getting out

PartlyYou keep ownership of recordings and transcripts, may request a copy of personal data and can set retention yourself, but no self-serve bulk export is documented and metrics export is an Enterprise line; billing is metered, so no prepaid credits can expire.You retain ownership of all content, data, audio, text, or media you submit through the Servicestelecho.io/legal/terms ↗

Certifications

YesSOC 2 Type II is claimed as attained with the report shown only under NDA, HIPAA is available through a signed BAA, and GDPR and UK GDPR are covered by a DPA with SCCs; ISO 27001 is not mentioned anywhere on the site.Attained. Report available to Enterprise Customers under NDAtelecho.io/security ↗