Text-to-speech

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

ElevenLabs · 8.27/10 for this job (curated estimate, high confidence)

capability voice quality + dx.

Runner-up

Cartesia · 7.81/10

Scores higher than the pick on: Price / performance, Privacy / data retention, Lock-in risk (higher = worse).

When not to use the pick

Already all-in on OpenAI and quality sufficient.

Lock-in / migration

Runner-up Cartesia has lower stored lock-in risk (4.5 vs 5.5, 0–10, higher = more lock-in). Self-host fallback listed for this job: Kokoro-82M, Piper, eSpeak NG.

Sourced price (usd_per_1k_characters)

Pick's lowest sourced SKU: Flash / Turbo Text to Speech $0.04 (usd_per_1k_characters) — source, as of 2026-10-03, re-checked 2026-10-27

Cheapest matching SKU: Deepgram Aura-2 $0.03 — source, as of 2026-10-03, re-checked 2026-10-27. Not the pick; not quality-adjusted.

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

Free option

• Cloudflare Workers AI text-to-speech (MeloTTS, Aura-1) (free) — source, as of 2026-10-19
• eSpeak NG (oss) — source, as of 2026-10-25
• Gemini 3.8 Flash TTS free tier (free tier unspecified) — source, as of 2026-10-26

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

Same-job, same-unit comparisons: ElevenLabs vs Deepgram

Cite: Agent Provider Depot, Depot Pick for speech-synthesis: elevenlabs, scores as of 2026-09-14. Agents: GET /api/decide?jtbd=speech-synthesis