PROVIDERLAST 30 DAYS

Guava voice AI models and benchmarks

Guava lists 2 STT and TTS models in Coval. Fastest dated mean latency over 30 days: STT: Daytona STT at 343 ms TTFS, with 4.3% WER. TTS: Daytona TTS at 357 ms TTFA, with 1.7% WER. Coval benchmarks hosted endpoints daily using a consistent evaluation methodology. Last measured .

Coval measures voice models created or hosted by Guava.

Measured models
2
STTTTS

Overview

Every model below is measured daily on the same fixed inputs and ranked against the full field, never blended into a company score.

Model lineup

Speech-to-Text
Daytona STT
Text-to-Speech
Daytona TTS

Ranked on Time to Final Segment against 30 measured models.

Time to Final Segmentms · lower is better · Guava models markedEvery measured STT model on Time to Final Segment, with Guava's models highlighted.
  1. #1Wire-128 ms
  2. #2Qwen3 ASR 1.7b35 ms
  3. #3STT RT v552 ms
  4. #5STT Rt v660 ms
  5. #6STT 170 ms
  6. #7Rumble-293 ms
  7. #25Daytona STT343 ms
leaders plus Guava models · 22 other models in the full table
Word Error Rate% · lower is better · Guava models markedEvery measured STT model on Word Error Rate, with Guava's models highlighted.
leaders plus Guava models · 23 other models in the full table
Time to First Tokenms · lower is better · Guava models markedEvery measured STT model on Time to First Token, with Guava's models highlighted.
  1. #1Wire-1766 ms
  2. #2Whisper Large v3919 ms
  3. #3Qwen3 ASR 1.7b944 ms
  4. #4STT 1999 ms
  5. #7Flux1097 ms
  6. #25Daytona STT5608 ms
leaders plus Guava models · 19 other models in the full table
Benchmarked models with their Time to Final Segment over the last 30 days.
ModelHostTTFSRank
Daytona STTGuava343 ms25th of 30

Ranked on Time to First Audio against 32 measured models.

Time to First Audioms · lower is better · Guava models markedEvery measured TTS model on Time to First Audio, with Guava's models highlighted.
  1. #1vui40 ms
  2. #2Default62 ms
  3. #3PhantomZ 4.065 ms
  4. #4TTS Flash 267 ms
  5. #6Simba 3.2101 ms
  6. #7Qwen3 TTS 1.7b104 ms
  7. #26Daytona TTS357 ms
leaders plus Guava models · 24 other models in the full table
Word Error Rate% · lower is better · Guava models markedEvery measured TTS model on Word Error Rate, with Guava's models highlighted.
leaders plus Guava models · 24 other models in the full table
Benchmarked models with their Time to First Audio over the last 30 days.
ModelHostTTFARank
Daytona TTSGuava357 ms26th of 32

How fast are Guava's STT and TTS models?

Daytona STT measures mean 343 ms time to final segment (25th of 30) among STT systems. Last measured 2026-11-18. Daytona TTS measures mean 357 ms time to first audio (26th of 32) among TTS systems. Last measured 2026-11-18.

How accurate are Guava's STT and TTS models?

Daytona STT measures 4.3% word error rate (22nd of 31) among STT systems. Last measured 2026-11-18. Daytona TTS measures 1.7% word error rate (14th of 32) among TTS systems. Last measured 2026-11-18.

Which Guava model is fastest?

Its fastest dated STT result is Daytona STT at mean 343 ms time to final segment (25th of 30) among STT systems, with 4.3% WER. Last measured 2026-11-18. Its fastest dated TTS result is Daytona TTS at mean 357 ms time to first audio (26th of 32) among TTS systems, with 1.7% WER. Last measured 2026-11-18.

Same datasets, prompts and metric definitions for every model, measured by Coval’s open-source runner. Full methodology on the overview.

Evaluate your own voice agent

Use Coval to test your production configuration, prompts and calls—not only the public benchmark endpoints.

Book a Demo