Package main implements an MCP server that provides text-to-speech functionality using macOS's built-in speech synthesis via /usr/bin/say.
Package googlespeech is a Genkit model plugin for Google Cloud speech: text to speech with Cloud Text-to-Speech (google/chirp3-hd, google/neural2, google/studio, google/wavenet and google/standard take the request's text and answer with an audio media part, a data URL of 16-bit PCM) and speech to text with Cloud Speech-to-Text v2 (google/chirp_3, google/chirp_2, google/chirp, google/long, google/short and google/telephony take an audio media part and answer with the transcript).
Package unisound searches system text-to-speech voices using Unisound MaaS.
Package edgetts turns text into speech with the online text-to-speech service of Microsoft Edge, without Edge, Windows or an API key.
Package voicekit is the official Go SDK for the VoiceKit API — Russian text-to-speech, speech-to-text with diarization, voice cloning, voice biometrics, audio/video effects, call QA, semantic search and batch jobs.
Package talkie is a voice front end for agents: wake word, voice activity detection, speech-to-text and text-to-speech with barge-in, on ONNX Runtime models (go-phonmatchnet, go-silero-vad, go-parakeet and go-kokoro) running in-process.
Package s2 provides Go bindings for s2.cpp, which runs Fish Audio S2 Pro text-to-speech through GGML.
Package htgotts turns text into speech: it asks a text-to-speech engine for the audio of a text and plays it, saves it to a file or hands it over as a stream or as bytes in memory.
Package synthesizer implements the Google Cloud Text-to-Speech adapter for ling-base.
Package synthesizer implements the Google Cloud Text-to-Speech adapter for ling-base.
Package synthesizer defines the core types and interfaces for text-to-speech synthesis.
Package synthesizer provides local (command-line) text-to-speech adapters that wrap system TTS tools such as say, espeak, festival and pico2wave.
Package synthesizer provides local (command-line) text-to-speech adapters that wrap system TTS tools such as say, espeak, festival and pico2wave.
Package cadence provides provider-agnostic voice AI engines: streaming speech-to-text, text-to-speech and LLM chat behind small uniform interfaces, plus the glue a real-time voice pipeline needs between them (sentence-aligned buffering for TTS, local energy VAD).
Package tts adds Text-to-Speech to togo.
Package google provides a Google Cloud Text-to-Speech implementation of the tts.Generation interface.
Package hydravox provides a resilient, high-performance Text-to-Speech (TTS) connection pool.
Package hydravox provides a resilient, high-performance Text-to-Speech (TTS) connection pool.
Package omnivoice provides a unified interface for speech-to-text and text-to-speech.
Command quickstart generates an audio file with the content "Hello, World!".
Golang module to generate text-to-speech using the TikTok API.
Package gotts is a text-to-speech package made using Google Translate's functionalities underhood.
Package synthesizer defines the core types and interfaces for text-to-speech synthesis.