Use Cases

Azure TTS voices for Documentary

Find Azure Text to Speech voices suited for Documentary. Compare voice gender, locale, speaking style, sample rate, and playable samples.

Voices 5
Style samples 20

Picks by requirement

Grouped from this page's matches using the Azure voice data: locale, model type, number of styles, and extra locales.

In your language

Widest style range

  • Yunze

    12 speaking styles · Chinese (Mandarin, Simplified)

Recommended voices

Ordered by use-case tags, voice traits, language support, and sample availability.

All use cases
Female

A bright, engaging voice with a beautiful tone that's perfect for delivering search results and capturing users' attention.

AngryDefaultFearfulSad 4 samples
en-US-AvaNeural

HD Flash version of Jimmie, with English and Chinese bilingual capability, deep, mature male voice with magnetic tone and natural gravitas, perfect for immersive storytelling, documentary narration, and character-driven dialogue.

General 1 samples
en-US-Jimmie:DragonHDFlashLatestNeural
Neutral

An objective neutral-sounding voice, good for conveying content without bias.

General 1 samples
en-US-BlueNeural
Female

An intellectual and comfort voice that is good for reading long contents.

General 1 samples
zh-CN-XiaoqiuNeural
Male

A deep, confident, and formal voice, ideal for delivering important information with authority and clarity.

AngryCalmCheerfulDefault 13 samples
zh-CN-YunzeNeural

Top matches side by side

Model type, style count, and sample count come from the Azure voice list.
VoiceLocaleGenderModelStylesSamples
Ava English (United States) Female Neural 4 4
Jimmie Dragon HD Flash Latest English (United States) Male HD 1 1
Blue English (United States) Neutral Neural 1 1
Xiaoqiu Chinese (Mandarin, Simplified) Female Neural 1 1
Yunze Chinese (Mandarin, Simplified) Male Neural 12 13