Eleven v4 Turbo in ElevenAgents vs Sume TTS as async jobs

Eleven v4 Turbo targets live agents. Sume TTS is an async job with poll or webhook and no streaming. Which one fits a call bot and which fits produced audio.

4 min readSume
All posts

Use Eleven v4 Turbo when a caller is waiting on a spoken reply, and Sume TTS when you are producing audio that a video, ad or app will play later. ElevenLabs says Turbo is live in ElevenAgents, ElevenCreative and the ElevenAPI (read 2026-10-07). Sume's TTS is an asynchronous job you poll or receive by webhook, and its streaming is a stated non-goal.

What ElevenLabs positions Turbo for

The v4 announcement lists a low-latency variant, Eleven v4 Turbo, alongside Eleven v4, with more than 90 languages and voice cloning from about 10 seconds of audio. The page quotes a median time to first speech of about 150 ms for Turbo (read 2026-10-07).

Eleven v4 Turbo and Sume TTS 1.0 delivery model - ElevenLabs figures (read 2026-10-07)
QuestionEleven v4 TurboSume TTS 1.0
DeliveryLow-latency, live agent useAsync job, poll or webhook
StreamingYes, per the product positioningNot offered (phase 1 non-streaming)
ResultAudio as it is producedSume-hosted audio artifact
Wait on submitNot applicableOptional sync wait up to 30 seconds

How a Sume TTS job behaves

mode: async returns at once with status_url and result_url. mode: sync and subscribe are the same bounded wait of up to 30 seconds; if the job is still running you get a timed-out flag and keep polling rather than resubmitting. mode: webhook delivers a signed terminal callback, with no partial or progress callbacks.

Synthesized audio longer than 1,200 seconds fails with tts_duration_exceeded, and no credit is captured for that failure. The TTS Router docs also list streaming TTS and an Eleven or OpenAI engine as out of scope for its first ship.

Pick by who is waiting

The third case is the one that fits both worlds. Many agent replies are fixed phrases such as greetings and confirmations, and a pre-rendered file has zero synthesis delay at call time.

  • A phone or chat agent that must answer mid-conversation: a streaming engine such as Eleven v4 Turbo.
  • A voice line used in a rendered video, an ad or a lesson: a Sume job, with the file saved once and reused.
  • A stock of canned replies for a live agent: render them ahead of time as Sume jobs, then play the files.

A pre-render submit

The pcm_mulaw at 8000 Hz output is one of the encodings and rates in the Sume schema, useful for telephony playback.

curl -X POST https://api.sume.com/v1/tts-1.0/generate \
  -H "Authorization: Bearer $SUME_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: greeting-line-001" \
  -d '{
    "transcript": "Thanks for calling. How can I help?",
    "avatar_handle": "speaker",
    "language": "en",
    "output_format": {"container": "wav", "encoding": "pcm_mulaw", "sample_rate": 8000},
    "mode": "webhook",
    "webhook_url": "https://example.com/webhooks/sume"
  }'

Sources

Related posts

More in Comparisons

All Comparisons posts

Written by Sume