ድምጺ
100+ AI voices across 20+ models. Find the perfect voice for your project. ድምጺ 20+ ሞዴላት 100+ AI voices across 20+ models.
200 ድምጺታት ተራእዩ
ድምጺ'ውን ኣይተገናኘን ምስ'ቲ መረጋገጺ'ዚ። ፈለጥካዮ መሰረታዊ ምትእስሳርካ ፈትሽ።
ቃላት ብAI ሞዴል
ሓደ ሓደ TTS ሞዴላት ናይቶም ድምጺታት ናይቶም ድምጺታት ናይቶም ድምጺታት ናይቶም ድምጺታት ናይቶም ድምጺታት ናይቶም ድምጺታት ናይቶም ድምጺታት ናይቶም ድምጺታት ናይቶም ድምጺታት ናይቶም ድምጺታት ናይቶም ድምጺታት ናይቶም ድምጺታት ናይቶም ድምጺታት ናይቶም ድምጺታት ናይቶም ድምጺታት ናይቶም ድምጺታት
Transformer-based text-to-audio model that generates realistic speech, music, and sound effects.
Bark Small
15 ቃላት
ቍጽሪ
ሞዴል ፈትሽ
Lighter version of Bark with faster inference and lower memory usage.
Chatterbox
1 ቃላት
ተለቪዥን
ሞዴል ፈትሽ
State-of-the-art zero-shot voice cloning with emotion control from Resemble AI.
Default
English
Chatterbox Turbo
1 ቃላት
ቍጽሪ
ሞዴል ፈትሽ
Faster Chatterbox with sub-200ms latency and paralinguistic tags for laughs, coughs, and more.
Default
English
CosyVoice 2
10 ቃላት
ቍጽሪ
ሞዴል ፈትሽ
Alibaba's scalable streaming TTS with human-parity naturalness and near-zero latency.
CosyVoice3
11 ቃላት
ቍጽሪ
ሞዴል ፈትሽ
Next-generation multilingual TTS with bi-streaming, emotion control, and zero-shot voice cloning.
Darwin TTS
4 ቃላት
ቍጽሪ
ሞዴል ፈትሽ
Cross-modal Qwen3-TTS variant with FFN weights blended from the Qwen3-1.7B language model for sharper multilingual cloning.
Multi-speaker dialog generation model that creates natural conversations between speakers.
Freya (Turkish)
Turkish
GPT-SoVITS
4 ቃላት
ቍጽሪ
ሞዴል ፈትሽ
Few-shot voice cloning TTS that replicates any voice from just 5 seconds of audio.
IndexTTS-2
2 ቃላት
ቍጽሪ
ሞዴል ፈትሽ
Zero-shot TTS with fine-grained emotion control and high expressiveness.
Indic Parler TTS
21 ቃላት
ቍጽሪ
ሞዴል ፈትሽ
High-quality speech for 8+ Indian languages with natural-language voice control.
Kani TTS 2
1 ቃላት
ቍጽሪ
ሞዴል ፈትሽ
Ultra-lightweight 400M English TTS model running in just 3GB VRAM.
Default
English
KhanomTan TTS
5 ቃላት
ቍጽሪ
ሞዴል ፈትሽ
Thai-first text-to-speech with a choice of speaker voices.
Kitten TTS
8 ቃላት
ነጻ
ሞዴል ፈትሽ
Ultra-lightweight TTS under 80MB. Runs on CPU without GPU.
Lightweight 82M parameter model delivering studio-quality speech with blazing-fast inference.
High-quality multilingual text-to-speech that runs on CPU with minimal latency.
Ming-Omni TTS
2 ቃላት
ነጻ
ሞዴል ፈትሽ
Compact 0.5B omni-modal speech model from inclusionAI with high-fidelity 44.1kHz output and zero-shot voice cloning.
MOSS-TTS Nano
11 ቃላት
ቍጽሪ
ሞዴል ፈትሽ
Tiny 100M MOSS-TTS variant — same architecture, 80x smaller, free-tier latency.
Multi-speaker dialogue continuation model — generate podcast-style conversations with up to 5 speakers and 60 minutes of coherent audio.
Instant voice cloning with granular control over style, emotion, and accent.
LLM-based TTS that runs on CPU, GPU, or browser via llama.cpp and Transformers.js.
Female 1 (Neutral)
ንግልጽነትን ንጥፈታት ውልቀ ሰባትን ጥራይ English
Parler TTS
1 ቃላት
ቍጽሪ
ሞዴል ፈትሽ
Describe the voice you want in natural language and Parler generates matching speech.
Default
EnglishA fast, local neural text to speech system optimized for Raspberry Pi and embedded devices.
Aegis (Urdu)
ንግልጽነትን ንጥፈታት ውልቀ ሰባትን ጥራይ UrduAivars (Latvian)
LatvianAlan (UK)
ንግልጽነትን ንጥፈታት ውልቀ ሰባትን ጥራይ EnglishAlba (UK)
ንግልጽነትን ንጥፈታት ውልቀ ሰባትን ጥራይ EnglishAmir (Persian)
ንግልጽነትን ንጥፈታት ውልቀ ሰባትን ጥራይ faAmy (US)
ንግልጽነትን ንጥፈታት ውልቀ ሰባትን ጥራይ EnglishAnna (Hungarian)
ንግልጽነትን ንጥፈታት ውልቀ ሰባትን ጥራይ HungarianAntton (Basque)
ንግልጽነትን ንጥፈታት ውልቀ ሰባትን ጥራይ Basqueድምጺ AI ንምፍላጥ
ደረጃታት ናይ ድምጺ ጥራሕ
TTS.ai ኣብ ሰለስተ ደረጃታት ጥራሕ ድምጺ ይቕረ በለ። ነጻ-ደረጃ ድምጺ ካብ Piper, VITS, and MeloTTS ዝህብ በብግዜኡ፣ ብቕዓት ጥሩፍ ስነ-ጽሑፍ ብቐሊሉ ይቕረ በለ። ስታንድርድ-ደረጃ ድምጺ ካብ ሞዴላት ከም Kokoro and CosyVoice 2 ዝህብ ንጹር ድምጺን ስነ-ስርዓትን ይቕረ በለ። ፕሪሚየም-ደረጃ ድምጺ ካብ OpenVoice, Chatterbox, and StyleTTS 2 ዝህብ እቲ ረዚን፣ ሰብ-እኩብ ድምጺ ዝህብ ኣብ open-source TTS
ድምጺ ቛንቋታት
ድምጺታት ብዛዕባኦም ቋንቋታት ብዛዕባኦም ይደግፉ። ገለ ሞዴላት ከም CosyVoice 2ን GPT-SoVITSን ድምጺታት ብዛዕባኦም ቋንቋታት ይደግፉ፣ ኣብኡ ድማ ድምጺ ኣብ ሓደ ቋንቋ ዝተማህረ ብባህሪኡ ኣብ ካልእ ቋንቋ ክዛረብ ይኽእል እዩ። እቲ ቋንቋታት ዝስዕብ ፎልደር ድምጺታት ንምርካብ ይሕግዘካ፡ ድምጺታት ንዘለኣለም ኣብ ቋንቋኻ ዝጸንሑ፣ እቲ ምርኣይን ምጽሓፍን ድምጺታት ንዘለኣለም ዝጸንሑ።
ድምጺ
ሓደስቲ ሞዴላት ክሎኒንግ ድምጺ ይደግፉ፣ እዚ ማለት፡ ድምጺ ከም መምርሒ ክትጥቀመሉ ትኽእል ኢኻ፡ ነቲ ሰብ ዝኣመሰለ ቃላት ንምፍጣር። ሓደ ድምጺ ዝሕብር ምሳሌ (10-30 ሰከንዶም) ኣትወጽእ፡ እቲ ሞዴል ድማ ነቲ ቃላት ንምምጻእ ይቕይር። ሞዴላት ክሎኒንግ ዝደግፉ፡ GPT-SoVITS፣ CosyVoice 2፣ Chatterbox፣ ወዘተ.
ድምጺ ፍትሒ ምጥቃም
እቲ ምርኣይ ድምጺ ኣብ ተግባርካ ይመርጽ። ንኦዲዮ-ብስክሪንታትን ፖድካስትታትን፡ ድምጺታት ተለፎን ተለፎን ምስ ስነ-ጥበባዊ ድምጺታት ተጠቒምካ። ንኻልኦት ኣርእስቲ፡ ድምጺታት ተለፎን ተለፎን ምስ ስነ-ጥበባዊ ድምጺታት ተጠቒምካ። ንኻልኦት ኣርእስቲ፡ ድምጺታት ቴሌፎን ምስ ስነ-ጥበባዊ ድምጺታት ተጠቒምካ።