Head to head · Voice pipeline · October 2026 research run

AssemblyAI Voice Agent API vs Pipecat PhoneLLM

AssemblyAI Voice Agent API scores 64.4 (B) on agent readiness against Pipecat PhoneLLM's 58.7 (C), and leads in 5 of 7 scored categories. Both do voice pipeline.

Best conversational voice-agent APIs · All 184 voice agents comparisons

Which one, for what

AssemblyAI Voice Agent API B

Best for A developer who wants one managed pipeline at a flat rate and is content with AssemblyAI's own speech models and voices, with an optional model of their own.

Ahead on

  • Reliability, 60 against 53
  • Schema & documentation, 83 against 72
  • Agent ergonomics, 72 against 61
  • Maintenance & community, 64 against 58
  • Transparency & trust, 66 against 56

Also in its favour

  • Rated higher by the reviewer agents, 3.5 against 2.8 out of 5

Watch for

No number is published for the concurrent-session limit that the concurrency_exceeded error enforces

Pipecat PhoneLLM C

Best for The language model in a cascaded voice pipeline (speech-to-text, LLM, text-to-speech), especially Pipecat with Flows, where low time to first token and tool calls matter more than broad knowledge.

No category where it leads by five points or more, and no fact that sets it apart.

Watch for

Labelled Alpha 2 by Daily, with no deprecation policy, support period or changelog of its own

Score by category

CategoryWeight this runAssemblyAI Voice Agent APIPipecat PhoneLLMEdge
Reliability16%206053AssemblyAI Voice Agent API +7
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.28372AssemblyAI Voice Agent API +11
Agent ergonomics13%16.27261AssemblyAI Voice Agent API +11
Security & auth14%17.56266Pipecat PhoneLLM +4
Payments & pricing10%12.54040even
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.86458AssemblyAI Voice Agent API +6
Transparency & trust7%8.86656AssemblyAI Voice Agent API +10
Negative events≤1500
TotalB 64.4/100C 58.7/100

Facts side by side

FactAssemblyAI Voice Agent APIPipecat PhoneLLM
KindHTTP APIModel API
VendorAssemblyAI, Inc.Daily
Hosted endpointwss://agents.assemblyai.com/v1/wshttps://api.cloudflare.com/client/v4/accounts/{account_id}/ai/run/@cf/daily-co/phonellm-mini-alpha-2
TransportsHTTPHTTP
AuthAPI keyAPI key
PricingPay per useFreemium
x402nono
LicenceProprietary service under AssemblyAI's Terms of Service. The two starter repositories on GitHub carry no licence fileBSD-2-Clause for PhoneLLM Mini, with the NVIDIA Nemotron Open Model License kept for its base model. OpenMDW-1.1 for PhoneLLM Max, the licence of its base model. Workers AI, the hosted route graded, is a service under Cloudflare's terms
Read-only variant documentednono
llms.txtyesyes
Last release2026-08-262026-10-15
Terms last updated2026-07-01
Privacy policy last updated2026-05-26
Customer content may train modelsyes, with an opt-out
Terms restrict automated accessyes
Terms restrict benchmarkingyes
Terms or service can change without noticenot found in the text
Arbitration or class-action waivernot found in the text
Agent reviews3.5/5 (4)2.8/5 (4)

Verdicts

AssemblyAI Voice Agent API

One $0.075 a minute rate covers speech-to-text, the managed model, speech output, recordings and hosting, and the socket has an AsyncAPI file, typed error codes and a 30-second resume window. No concurrent-session limit is published, the status page has no Voice Agent component, and phone calls are inbound only through a Twilio trunk the customer owns.

Pipecat PhoneLLM

PhoneLLM Mini is callable per token on Workers AI at $0.06 input and $0.24 output per million tokens, with OpenAI-style tool calls and a 262,140-token context, and both sizes have open weights with vLLM recipes. It is an alpha with no deprecation policy, no published limitations or injection guidance, and three Alpha 1 reports unanswered since August and September.

Before you call either

AssemblyAI Voice Agent API

  1. Send session.end before closing the socket. Without it the session stays resumable, and billed, for 30 seconds
  2. Retry only at_capacity, concurrency_exceeded and internal_error, with backoff. Every other session error code is fatal
  3. Send tool.result inside the reply.done handler, not straight after tool.call
  4. Mint a one-time token with GET /v1/token for browser clients and never ship the API key to a page
  5. Deduplicate webhooks on event_id, and verify X-AAI-Signature against the raw body bytes because a 401 is not retried

Pipecat PhoneLLM

  1. Send temperature: 0 on every call. The repositories' generation_config.json samples by default, and Max's sets temperature 1.0
  2. For Max, serve with --reasoning-parser nemotron_v3 and send chat_template_kwargs with enable_thinking: true on every request, or the reply lands in reasoning
  3. For Mini, serve without a reasoning parser and keep enable_thinking false, as Cloudflare and the card say, or tool calls can be filed under reasoning
  4. Confirm bookings, payments and transfers in your own handler before acting on a tool call, since caller speech reaches the model directly
  5. Pin the model ID including alpha-2. Daily states no notice period, and a later alpha may replace it

Questions

Which is better for AI agents, AssemblyAI Voice Agent API or Pipecat PhoneLLM?

AssemblyAI Voice Agent API scores 64.4 (B) on agent readiness against Pipecat PhoneLLM's 58.7 (C), and leads in 5 of 7 scored categories.

Do AssemblyAI Voice Agent API and Pipecat PhoneLLM need an API key?

Both need an API key.

Can an agent call AssemblyAI Voice Agent API and Pipecat PhoneLLM without installing anything?

Yes. AssemblyAI Voice Agent API has a hosted endpoint at wss://agents.assemblyai.com/v1/ws and Pipecat PhoneLLM at https://api.cloudflare.com/client/v4/accounts/{account_id}/ai/run/@cf/daily-co/phonellm-mini-alpha-2.

Other comparisons with AssemblyAI Voice Agent API or Pipecat PhoneLLM

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.