-
LoginSelect language Europe and America 🇺🇸 English (ALL) 🇫🇷 Français (French) 🇩🇪 Deutsch (Germany) 🇪🇸 Español (Spanish) 🇮🇹 Italiano (Italian) 🇧🇷 Português (Portuguese) 🇷🇺 Русский (Russian) 🇹🇷 Türkçe (Turkish) 🇫🇮 Suomi (Finnish) 🇸🇪 Svenska (Sweden) 🇳🇴 Norsk (Norwegian) 🇩🇰 Dansk (Danish) 🇷🇴 Română (Romanian) 🇭🇺 Magyar (Hungarian) 🇵🇱 Polski (Polish) 🇳🇱 Nederlands (Dutch) 🇨🇿 Čeština (Czech) 🇺🇦 Українська (Ukrainian) 🇭🇷 Hrvatski (Croatian) 🇬🇷 Ελληνικά (Greek) 🇸🇰 Slovenčina (Slovak) 🇧🇬 Български (Bulgarian) 🇸🇮 Slovenščina (Slovenian) ca Català (Catalan) 🇮🇪 Gaeilge (Irish) 🇱🇹 Lietuvių (Lithuanian) 🇲🇹 Malti (Maltese) 🇪🇪 Eesti (Estonian) 🇮🇸 Íslenska (Icelandic) 🇱🇻 Latviešu (Latvian) 🇬🇧 Welsh (Cymraeg) 🇲🇰 Macedonian (Македонски) 🇧🇦 Bosnian (Bosanski) 🇪🇸 Galician (Galego) 🇺🇿 Uzbek (Oʻzbekcha) 🇷🇸 Serbian (Српски) 🇨🇦 Inuktitut (ᐃᓄᒃᑎᑐᑦ) 🇨🇦 Inuktitut (Latin) Asia and Africa 🇨🇳 中文 (简体/Simplified Chinese) 🇭🇰 中文 (繁體/Traditional Chinese) 🇰🇷 한국 (Korean) 🇯🇵 日本語 (Japanese) 🇻🇳 Việt (Vietnam) 🇲🇾 Melayu (Malaysia) 🇮🇩 Indonesia (Indonesia) 🇹🇭 ภาษาไทย (Thai) 🇦🇪 Arabic (العربية) 🇮🇱 בעברית (Israel) 🇮🇳 हिंदी (Hindi) 🇮🇳 اردو (Urdu) 🇮🇳 தமிழ் (Tamil) 🇮🇳 मराठी (Marathi) 🇮🇳 తెలుగు (Telugu) 🇮🇳 ગુજરાતી (Gujarati) 🇮🇳 മലയാളം (Malayalam) 🇧🇩 বাংলা (Bengali) 🇮🇳 ಕನ್ನಡ (Kannada) sw Kiswahili (Swahili) 🇿🇦 Afrikaans 🇿🇦 Zulu (IsiZulu) 🇦🇿 Azerbaijani (Azərbaycanca) 🇮🇩 Javanese (ꦧꦱꦗꦮ) 🇬🇪 Georgian (ქართული) 🇰🇿 Kazakh (Қазақша) 🇰🇭 Khmer (ភាសាខ្មែរ) 🇱🇦 Lao (ລາວ) 🇲🇳 Mongolian (Монгол) 🇲🇲 Burmese (ဗမာ) 🇳🇵 Nepali (नेपाली) 🇦🇫 Pashto (پښتو) 🇱🇰 Sinhalese (සිංහල) 🇸🇴 Somali (Soomaali) 🇮🇳 Assamese (অসমীয়া) 🇦🇲 Armenian (Հայերեն) 🇮🇳 Odia (ଓଡ଼ିଆ) 🇮🇳 Punjabi (ਪੰਜਾਬੀ)
AI Voice Library
Filters
No AI voices found matching your criteria. Please reset your search or filter to try again.
Your favorite voices will appear here
Dialogue Block Conversion History Dialogue Block Conversion History Demo
Here are the conversion records of this Dialogue Block from the past 24 hours.
No conversion history yet
No conversion records found for this Dialogue Block. Please convert the Dialogue Block to speech first.
#[[ index + 1 ]]
Latest [[ history_panel.current_block.ai_voice_config.name || 'Voice' ]] [[ format_history_time(record.create_time) ]]
[[ format_expire_time_display(record) ]]
Voice Speed: [[ record.speed ]]x |
Voice Volume: [[ (parseFloat(record.volume) *
100).toFixed(0) ]]% |
Pitch: [[ record.pitch ]]
| Emotion: [[ format_emotion_display(record) ]]
To protect your privacy, conversion records and temporary download links are only stored for 24 hours. Files older than 24 hours are deleted, and download links become invalid.
No conversion records found for this Dialogue Block. Please convert the Dialogue Block to speech first.
Generate All Dialogue Blocks
Total Progress
[[generate_all.progress_percent]]%
Status
[[generate_all.status_text]]
[[generate_all.success_blocks ? generate_all.success_blocks.length : 0]]
Successful
[[generate_all.failed_blocks ? generate_all.failed_blocks.length : 0]]
Failed
Current Failed Dialogue Blocks:
[[failed_block.block_id]]: [[failed_block.error]]
Audio Export History Demo
No conversion history yet
Click the Generate Dialogue Audio button to create new merged audio files
To protect your privacy, conversion records and temporary download links are only stored for 24 hours. Files older than 24 hours are deleted, and download links become invalid.
Generated Audio Files
Download or play your generated audio files.
Expired audio files are automatically filtered out
#[[index + 1]] Latest
Created: [[format_history_time(merge_record.create_time)]]Dialogue Blocks: [[merge_record.blocks_count]] files processed
[[format_expire_time_display_for_merge(merge_record)]]
Generate All Settings
ms
: 0-10000ms
(0-10 seconds)
Current Settings Preview:
- Audio Format: [[generate_all.settings.audio_format.toUpperCase()]]
- Audio Quality: [[generate_all.settings.voice_high_quality ? "High Quality (large size, slow synthesis)" : "Standard Quality (small size, fast synthesis)"]]
- Pause Interval Between Dialogue Blocks: [[get_current_pause_interval()]]
Send Feedback
Upgrade plan
Subscription Adjustment Alert: Self-service plan changes are not yet available. For upgrades or downgrades, email to [email protected] for assistance.
Upgrade Required
Upgrade to Pro/Studio to unlock all premium features!
Current demo mode lets you explore the interface and basic features of the AI Voice Dialogue Generator.
The AI Voice Dialogue Generator feature is exclusively available to users with the following subscription levels: Pro/Studio.
Explore the basic functionality here. To create, edit, rename, or delete projects, please upgrade to a Pro or Studio subscription (Lite plan not supported).
| Plan & Features | AI Voice Generator (Single Speaker) |
AI Voice Dialogue Generator (Multi-Speaker Dialogue) |
Multi-emotional Settings (Emotion) |
API support API for Developers |
|---|---|---|---|---|
| Free | Not Available | Not Available | Not Available | Not Available |
| Lite | Available | Not Available | Not Available | Not Available |
| Pro/Studio | Available | Available | Available | Available |
Loading...
[[ block.order + 1 ]]- Block
Speed [[ formatSpeedButtonText(block.speed) ]]
[[ formatSpeedDisplay(block.speed) ]]
-50%
0%
+100%
Advanced
-
Usage tips:
- Characters (Pronounce as characters)
- Cardinal (Pronounce as a number)
- Ordinal (Pronounce as an ordinal)
- Digits (Pronounce as digits)
- Fraction (Pronounce as a fraction)
- Date (Pronounce as a date)
- Time (Pronounce as time)
- Telephone (Pronounce as a phone number)
- Currency (Pronounce as currency)
- Address (Pronounce as an address)
- Name (Pronounce as a name)
To use say-as, first select the text you want to mark, then choose a tag. Or, insert a tag and fill in the content between the tags. This helps the TTS engine interpret the text in a specific way (e.g., as a date, address, etc.).
Example:
<say-as interpret-as="telephone">123-456-7890</say-as>
-
Usage tips:
- Strong (Strong emphasis level)
- Moderate (Moderate emphasis level)
- Reduced (Reduced emphasis level)
After adding the emphasis tag, write the text you want to emphasize between the tags. You can choose the emphasis level: strong, moderate, or reduced. This will make the TTS engine stress the selected text accordingly.
Example:
<emphasis level="moderate">Hello</emphasis>
-
Usage tips:
- Insert phoneme tag
Step 1: Add the phoneme tag to your word or phrase. Step 2: Replace the value in ph= with the correct IPA pronunciation. You can use ChatGPT or other tools to generate the IPA for your word.
Example:
<phoneme alphabet="ipa" ph="tə.ˈmeɪ.toʊ">tomato</phoneme>
[[
block.announcer_id ]]
[[block.ai_voice_config.name]]
[[block.ai_voice_config.standard_language_code]]
[[ block.text.length ]]/[[ max_block_chars ]]
[[ bottom_audio_player.is_visible ? "Hide Player" : "Show Player" ]]