Full voice-agent platform (STT+TTS+orchestration)

Scores as of 2026-09-14 (43 days old; Depot marks scores stale after 30 days). The pick is still Depot's current editorial pick; it has not been re-reviewed since. Prices below carry their own dates.

Depot Pick

Vapi · 8.25/10 for this job (curated estimate, high confidence)

End-to-end capability to ship without stitching. Round 4: Vapi is the actual orchestration SKU; Deepgram remains production-stt pick. Watch Deepgram Flux TTS promo expiry 2026-09-14.

Runner-up

Bland AI · 7.91/10

Scores higher than the pick on: Price / performance, Privacy / data retention.

When not to use the pick

Want OSS realtime media control and to compose models yourself — LiveKit; STT-quality is the product — Deepgram; already on Cartesia Sonic+Ink and only need their voice agent minutes.

Lock-in / migration

The pick has lower stored lock-in risk than runner-up Bland AI (5 vs 6.5).

Sourced price (usd_per_minute)

Pick's lowest sourced SKU: Vapi hosting $0.05 (usd_per_minute) — source, as of 2026-10-03, re-checked 2026-10-27

Cheapest matching SKU: Vapi Vapi hosting $0.05 — source, as of 2026-10-03, re-checked 2026-10-27. The pick is the cheapest.

Price history: first seen 2026-10-03 · last changed no change recorded · history JSON

Free option

No free resource lists this job. A cheap paid SKU is not a free option.

Failure modes to watch

• Runaway spend: Set a budget and a tool-call cap per task. Alert when spend jumps. Stop the run at the cap instead of summarizing a partial trace as success.
• Confirmation skip: Gate those tool names on an approval id recorded before the call. A missing approval is a failure even if the downstream tool returns success.
• Identity confusion: Bind every tool call to a user or tenant id. Refuse the call if that id changed mid-task. For a public bot, the operator owns the words the bot shows.
• Non-determinism: Run the task more than once and compare the end state, not a single transcript. Record the trial count next to any success rate you cite.
• Over-refusal: Log refusals separately from successes. Review a sample against the written policy. Do not treat a refusal as a pass, and do not weaken a safety check to raise the pass rate.
• Partial tool success: Require a per-item status and a failure count. Success for the task requires the failed count to be zero or explicitly handed to a retry queue.

Reported outcomes (submitted reports only)

This job: loading… JSON · reports never change scores · seed/test records excluded

Depot Pick (Vapi) on this job: loading… JSON · reports never change scores · seed/test records excluded

Cite: Agent Provider Depot, Depot Pick for voice-agent-platform: vapi, scores as of 2026-09-14. Agents: GET /api/decide?jtbd=voice-agent-platform