Voice & audio

Text-to-speech & voice cloning

194 agents · most starred first

Text-to-speech & voice cloning, page 2 of 2

GPT-SoVITS-v2★ 4

gradio region:us

GPT-SoVITS-v2-VC★ 4

gradio region:us

clone-voice★ 4

🎙️ Agent Skill — Offline zero-shot voice cloning with Qwen3-TTS 0.6B. Drop a reference audio + text, get cloned speech. CPU/MPS/CUDA, 10 languages.

sarvam-bridge★ 4

Point your existing ElevenLabs, OpenAI Audio or Deepgram app at Sarvam AI by changing one line. Drop-in compatibility gateway for Indic TTS & STT on Bulbul and Saaras: script-aware language detection, grapheme-safe Hindi/Tamil chunking, CER-based voice mapping, caching + request coalescing. TypeScript, Docker, 168 tests, MIT.

OpenAI-Spechify-Your-Docs★ 4

OpenAI-Spechify-Your-Docs is a Python project that converts text from `.txt`, `.pdf`, and `.epub` files into speech using OpenAI's Text-to-Speech API.

Twitch-AI-Newscaster★ 4

Create a text to speech AI host for Twitch

GPT-SoVITS-Trilingual★ 3

gradio region:us

indic-parler-tts★ 3

gradio region:us

GPT-SoVITS-v-3★ 3

gradio region:us

GPT-SoVITS-v2★ 3

gradio region:us

elevenlabs-v3-text-optimization★ 3

Free Claude Skill that rewrites any text into ElevenLabs V3-optimized scripts — audio tags, pacing, phonetic respelling & acronym/number normalization for better AI voice synthesis.

eddiTTS★ 2

An interactive AI Voice assistant extension for EDDI

vits-chatbot★ 2

gradio region:us

Multi-voice-TTS-GPT-SoVITS★ 2

gradio region:us

GPT-SoVITS-VC-2★ 2

gradio region:us

GPT-SoVITS★ 2

gradio region:us

gpt-sovits★ 2

docker region:us

gpt-sovits-deniya★ 2

docker region:us

facebook-fastspeech2-en-ljspeech★ 2

gradio region:us

Cartesia Sonic-3

Instant AI voices that laugh and show real emotion.

ElevenLabs

Generate realistic AI voices, audiobooks, and conversational AI.

Hume AI

Create AI voices that sound real and understand emotions.

Rime

Rime gives your AI human-like voices for better customer talks.

Kokoro TTS

Turn your text into natural, high-quality voices across many languages.

Natural TTS Labs

Turn text into lifelike speech with AI voices. Easy and free!

@ai-sdk/elevenlabs

The **[ElevenLabs provider](https://ai-sdk.dev/providers/ai-sdk-providers/elevenlabs)** for the [AI SDK](https://ai-sdk.dev/docs) contains speech generation plus batch and realtime transcription support for the ElevenLabs APIs.

@ai-sdk/lmnt

The **[LMNT provider](https://ai-sdk.dev/providers/ai-sdk-providers/lmnt)** for the [AI SDK](https://ai-sdk.dev/docs) contains language model support for the LMNT API.

AudioChatGpt

A simple project to make ChatGpt speak

GPT-SoVITS-Infer

Inference code for GPT-SoVITS

TellMeFriday

A simple tool based on gtts(google text to speech api)

chatgptTTS

This is the simplest module for AI Conversations with TTS.

chatterbox-vllm

Chatterbox TTS ported to VLLM for efficienct and advanced inference tasks

claude-voice

TTS with karaoke-style word highlighting for Claude Code. Fully local, zero API keys, one file.

elevenlabs-haystack

ElevenLabs Text-to-Speech components for Haystack.

farm-haystack-text2speech

Haystack node to convert text entities (documents, answers, etc...) into audio files.

gemini-tts

A Python package for Gemini Text-to-Speech using the official API.

gpt-sovits-python

Python wrapper for fast inference with GPT-SoVITS

gptspeak

Text-to-speech CLI tool and Python library using OpenAI's TTS API

langchain-camb

LangChain integration for CAMB AI - multilingual audio and localization tools

livekit-plugins-openai-sse

Agent Framework plugin for OpenAI Server-Sent Events TTS API

livekit-plugins-openai-sse-tts

Agent Framework plugin for OpenAI Server-Sent Events TTS API

llama-index-tools-azure-speech

llama-index tools azure_speech integration

llama-index-tools-elevenlabs

llama-index tools elevenlabs integration

llama-index-tools-typecast

llama-index tools typecast integration

llm-azure-tts

Text-to-speech using the Azure OpenAI TTS API

llmbot_plugin_reecho_voice

Generate Voice From reecho.ai Api In OpenAiBot.

nonebot-plugin-gpt-sovits

✨ NoneBot2 Plugin for GPT-SoVITS ✨

openai-tts

A powerful and easy-to-use Python library for generating natural-sounding speech using OpenAI text-to-speech capabilities.

openai-tts-tool

A CLI that provides tts using OpenAI

openai-voicestream

A library for real-time text to speech processing using OpenAI API.

tts-webui-extension.gpt-sovits

Placeholder for tts_webui_extension.gpt_sovits until migrated from GitHub due to VCS dependencies.

tts-webui-extension.openai-tts-api

OpenAI compatible TTS API with support for multiple TTS models

twelve-ai-agents

A library to convert text to Morse code and play it as audio.

videosdk-plugins-groq

VideoSDK Agent Framework plugin for Groq TTS services

vision-agents-plugins-elevenlabs

ElevenLabs TTS and STT integration for Vision Agents

vision-agents-plugins-fish

Fish Audio TTS and STT integration for Vision Agents

vision-agents-plugins-kokoro

Kokoro TTS integration for Vision Agents

vision-agents-plugins-pocket

Pocket TTS integration for Vision Agents - lightweight CPU-based text-to-speech

voicegpt

voice cloning with GPT

yarngpt

A Python wrapper for YarnGPT text-to-speech model with multi-language support

yarngpt-sdk

Unofficial community Python SDK for YarnGPT - Text-to-Speech API for Nigerian Accents

@diffusionstudio/piper-wasm

Wasm build of rhasspy / piper

langvoice-sdk

JavaScript/TypeScript SDK for LangVoice Text-to-Speech API with AI agent integrations

LMNT

Make voices from text, clone any voice fast and lifelike.

Coqui TTS

Turn text into natural speech, clone voices, and support many languages.

tiktok-voice-generator

TikTok Voice Generator review: compare features, pricing, use cases, access model, and alternatives for this Voice AI Agents agent in 2026. AI-powered text-to-speech generator for TikTok content creation

fine-voice

Fine Voice review: compare features, pricing, use cases, access model, and alternatives for this Voice AI Agents agent in 2026. Free online AI voice generator and text-to-speech studio with voice cloning and API

pipecat-xtts-vllm

Pipecat community TTS integration for the XTTSv2-vLLM streaming server

agent-core-voice

Voice synthesis endpoint for agent_core — per-agent Qwen3-TTS via ICL voice cloning

agent-voice

Local, free voice artifacts for AI agents

langchain-flowspeech

LangChain tools for FlowSpeech text-to-speech generation.

runapi-gemini-tts

RunAPI Gemini TTS SDK for multi-speaker speech generation in JavaScript, Python, Ruby, Go, Java, and PHP

runapi-openai-tts

RunAPI OpenAI TTS SDK for speech generation in JavaScript, Python, Ruby, Go, Java, and PHP

gandr-haystack

Gandr text to speech component for Haystack

swarmauri_agent_texttospeech

Stateless Swarmauri agent for converting independent text prompts into audio through any TTSBase provider.

swarmauri_tts_playht

Deprecated Play.ht compatibility package; migrate to swarmauri_standard OpenaiTTS.

speech-generation

Speech Generation review: compare features, pricing, use cases, access model, and alternatives for this Voice AI Agents agent in 2026. Free online text-to-speech AI that converts text to natural human-like audio.

gandr-crewai

CrewAI text to speech tool for the Gandr TTS API. First audio byte in 146 ms over the open internet, 116 ms p50 first audio, server side warm. 23 languages, every render watermarked.

gandr-langchain

LangChain text to speech tool for the Gandr TTS API. First audio byte in 146 ms over the open internet, 116 ms p50 first audio, server side warm. 23 languages, every render watermarked.

vision-agents-plugins-speechify

Speechify TTS integration for Vision Agents

Fish Audio - the most realistic AI voice generator

AI-powered text-to-speech (TTS) voice generator and voice cloning platform designed to create highly realistic, emotional, and lifelike audio.

read-aloud-reader

Read aloud reader review: compare features, pricing, use cases, access model, and alternatives for this Productivity agent in 2026. READ ALOUD. READ TEXT OUT LOUD.

pydantic-ai-tts

Speak pydantic-ai streamed output aloud, as it streams

@ai-sdk/cartesia

The **[Cartesia provider](https://ai-sdk.dev/providers/ai-sdk-providers/cartesia)** for the [AI SDK](https://ai-sdk.dev/docs) contains Sonic 3.5 speech generation, Ink-Whisper batch transcription, and Ink 2 realtime and streaming transcription support.

@ai-sdk/fish-audio

The **[Fish Audio provider](https://ai-sdk.dev/providers/ai-sdk-providers/fish-audio)** for the [AI SDK](https://ai-sdk.dev/docs) contains speech generation (S1 and S2 models) and speech-to-text transcription support.

agents-local-tts

Ultralight CLI for local text-to-speech, powered by Kokoro by default

gpt-sovits-cpufast

CPU-focused inference fork of GPT-SoVITS

@framers/agentos-ext-streaming-tts-openai

Streaming TTS via OpenAI Audio Speech API with adaptive sentence chunking for AgentOS voice pipeline

lazybird-haystack

Lazybird text to speech for Haystack: natural AI voices (MP3) in your pipelines and agents, 500+ voices in 150+ languages.

llama-index-tools-lokutor

llama-index tools lokutor integration: give agents Lokutor text-to-speech and speech-to-text

lokutor-haystack

Lokutor text-to-speech and speech-to-text components for Haystack

Play HT

AI text-to-speech and voice generator with natural voices in many languages, usable from the browser.

LOVO AI

AI voice generator and text-to-speech studio with natural voices in many languages, usable from the browser.

Loquendo

AI text-to-speech and Loquendo-style voice generator with natural voices, usable from the browser.

More in Voice & audio