---
type: "raw_signal"
id: "26-best-text-to-speech-models-for-voice-07271f"
slug: "26-best-text-to-speech-models-for-voice-07271f"
title: "26 Best Text-to-Speech Models for Voice Agents 2026 (Tested)"
description: "Cekura has published a text-to-speech benchmark for voice agents, presenting results for 26 models and separating streaming latency, accuracy, naturalness, price, and stopping behavior."
retrieval_nugget: "Cekura has published a text-to-speech benchmark for voice agents, presenting results for 26 models and separating streaming latency, accuracy, naturalness, price, and stopping behavior."
observed_at: "2026-10-20"
record_date: "2026-10-20"
date_kind: "observed_at"
why_it_matters: "Cekura has published a text-to-speech benchmark for voice agents, presenting results for 26 models and separating streaming latency, accuracy, naturalness, price, and stopping behavior. Its leaderboard reports Inworld TTS-2 Flash at 45 ms streaming latency, 93.2% accuracy, and $15 per million characters; Gradium TTS is reported to begin speaking before the final word arrives on tested streaming in"
novelty: "notable"
verification_level: "source-linked"
signal_type: "research"
source_platform: "benchmarks.cekura.ai"
topics: []
entities: ["Cekura","Inworld TTS-2 Flash","Gradium TTS"]
related_patterns: []
novelty_label: "new_fact"
what_changed: "Cekura adds a 26-model benchmark focused on voice-agent TTS, comparing streaming latency, accuracy, naturalness, pricing and stop behavior; the prior Open TTS leaderboard covers multilingual TTS and voice cloning."
prior_refs: ["memory:a9f933d4-69a8-8919-a74e-4f168aa7fa65","memory:7a9b5868-03c5-801f-a558-8028fd75413a"]
source_url: "https://benchmarks.cekura.ai/text-to-speech"
source_urls: ["https://benchmarks.cekura.ai/text-to-speech"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "signal:26-best-text-to-speech-models-for-voice-07271f"
status: "published"
visuals: []
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/signals/26-best-text-to-speech-models-for-voice-07271f/","markdown":"https://newruntime.com/signals/26-best-text-to-speech-models-for-voice-07271f.md","json":"https://newruntime.com/signals/26-best-text-to-speech-models-for-voice-07271f.json"}
---

# 26 Best Text-to-Speech Models for Voice Agents 2026 (Tested)

## Retrieval answer

Cekura has published a text-to-speech benchmark for voice agents, presenting results for 26 models and separating streaming latency, accuracy, naturalness, price, and stopping behavior.

Cekura has published a text-to-speech benchmark for voice agents, presenting results for 26 models and separating streaming latency, accuracy, naturalness, price, and stopping behavior. Its leaderboard reports Inworld TTS-2 Flash at 45 ms streaming latency, 93.2% accuracy, and $15 per million characters; Gradium TTS is reported to begin speaking before the final word arrives on tested streaming inputs, with 79.5% accuracy. The page notes that accuracy and naturalness are estimates and that eight voices unable to take streamed text are not shown in the streaming chart. The benchmark gives builders a comparative starting point, but its measures and test conditions should not be treated as a universal ranking. Source: https://benchmarks.cekura.ai/text-to-speech

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- collection: [Raw Signals](https://newruntime.com/signals.json): Open every source-linked raw signal.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)