Directories
¶
| Path | Synopsis |
|---|---|
|
Package anthropic is a streaming LLM service backed by the Anthropic API.
|
Package anthropic is a streaming LLM service backed by the Anthropic API. |
|
Package assemblyai is a streaming speech-to-text service backed by AssemblyAI's Universal-Streaming (v3) WebSocket.
|
Package assemblyai is a streaming speech-to-text service backed by AssemblyAI's Universal-Streaming (v3) WebSocket. |
|
Package asyncai is a streaming text-to-speech service backed by Async's TTS WebSocket.
|
Package asyncai is a streaming text-to-speech service backed by Async's TTS WebSocket. |
|
aws
|
|
|
bedrock
Package bedrock provides a streaming LLM service for Anthropic Claude models served through Amazon Bedrock.
|
Package bedrock provides a streaming LLM service for Anthropic Claude models served through Amazon Bedrock. |
|
novasonic
Package novasonic is a speech-to-speech service built on Amazon Nova Sonic, served over Bedrock's bidirectional streaming API.
|
Package novasonic is a speech-to-speech service built on Amazon Nova Sonic, served over Bedrock's bidirectional streaming API. |
|
polly
Package polly is a text-to-speech service backed by Amazon Polly's SynthesizeSpeech API.
|
Package polly is a text-to-speech service backed by Amazon Polly's SynthesizeSpeech API. |
|
transcribe
Package transcribe is a streaming speech-to-text service backed by Amazon Transcribe's StartStreamTranscription API.
|
Package transcribe is a streaming speech-to-text service backed by Amazon Transcribe's StartStreamTranscription API. |
|
azure
|
|
|
openai
Package openai provides an LLM and a transcription service for Azure OpenAI.
|
Package openai provides an LLM and a transcription service for Azure OpenAI. |
|
realtime
Package realtime is a speech-to-speech service built on Azure OpenAI's Realtime API.
|
Package realtime is a speech-to-speech service built on Azure OpenAI's Realtime API. |
|
speech
Package speech provides Azure AI Speech services.
|
Package speech provides Azure AI Speech services. |
|
Package camb is a streaming text-to-speech service backed by Camb.ai's MARS models.
|
Package camb is a streaming text-to-speech service backed by Camb.ai's MARS models. |
|
Package cartesia is a streaming text-to-speech service backed by Cartesia's TTS WebSocket.
|
Package cartesia is a streaming text-to-speech service backed by Cartesia's TTS WebSocket. |
|
Package cerebras provides Cerebras's OpenAI-compatible LLM service.
|
Package cerebras provides Cerebras's OpenAI-compatible LLM service. |
|
Package deepgram provides Deepgram's streaming speech-to-text service (over the live transcription WebSocket, see stt.go), its Aura text-to-speech service (see tts.go), and its Flux streaming STT and TTS services (see flux.go and flux_tts.go).
|
Package deepgram provides Deepgram's streaming speech-to-text service (over the live transcription WebSocket, see stt.go), its Aura text-to-speech service (see tts.go), and its Flux streaming STT and TTS services (see flux.go and flux_tts.go). |
|
Package deepseek provides DeepSeek's OpenAI-compatible LLM service.
|
Package deepseek provides DeepSeek's OpenAI-compatible LLM service. |
|
Package elevenlabs is a streaming text-to-speech service backed by ElevenLabs.
|
Package elevenlabs is a streaming text-to-speech service backed by ElevenLabs. |
|
Package fal is a batch speech-to-text service backed by Fal's Wizper API.
|
Package fal is a batch speech-to-text service backed by Fal's Wizper API. |
|
Package fireworks provides Fireworks AI's OpenAI-compatible LLM service.
|
Package fireworks provides Fireworks AI's OpenAI-compatible LLM service. |
|
Package fish is a streaming text-to-speech service backed by Fish Audio.
|
Package fish is a streaming text-to-speech service backed by Fish Audio. |
|
Package gladia is a streaming speech-to-text service backed by Gladia's Live STT v2 API.
|
Package gladia is a streaming speech-to-text service backed by Gladia's Live STT v2 API. |
|
google
|
|
|
gemini
Package gemini is a streaming LLM service backed by Google's Gemini API (generateContent with SSE).
|
Package gemini is a streaming LLM service backed by Google's Gemini API (generateContent with SSE). |
|
live
Package live is a speech-to-speech service built on Google's Gemini Live API (BidiGenerateContent).
|
Package live is a speech-to-speech service built on Google's Gemini Live API (BidiGenerateContent). |
|
vertex
Package vertex provides Google's Gemini models as served by Vertex AI: a streaming LLM (NewLLM) and the Live speech-to-speech service (NewS2S).
|
Package vertex provides Google's Gemini models as served by Vertex AI: a streaming LLM (NewLLM) and the Live speech-to-speech service (NewS2S). |
|
Package gradium provides Gradium's speech services: streaming text-to-speech and real-time streaming speech-to-text, both over Gradium's WebSocket API.
|
Package gradium provides Gradium's speech services: streaming text-to-speech and real-time streaming speech-to-text, both over Gradium's WebSocket API. |
|
Package groq provides Groq's OpenAI-compatible LLM service and its Whisper speech-to-text and text-to-speech services.
|
Package groq provides Groq's OpenAI-compatible LLM service and its Whisper speech-to-text and text-to-speech services. |
|
Package hume is a streaming text-to-speech service backed by Hume AI's Octave TTS.
|
Package hume is a streaming text-to-speech service backed by Hume AI's Octave TTS. |
|
Package inception provides Inception's OpenAI-compatible LLM service.
|
Package inception provides Inception's OpenAI-compatible LLM service. |
|
Package inworld is a streaming text-to-speech service backed by Inworld AI's HTTP streaming endpoint.
|
Package inworld is a streaming text-to-speech service backed by Inworld AI's HTTP streaming endpoint. |
|
Package kokoro is a text-to-speech provider for a local Kokoro-FastAPI server.
|
Package kokoro is a text-to-speech provider for a local Kokoro-FastAPI server. |
|
Package kyutai provides Kyutai's self-hosted speech services.
|
Package kyutai provides Kyutai's self-hosted speech services. |
|
Package lmnt is a streaming text-to-speech service backed by LMNT's HTTP "speech bytes" endpoint, which streams raw PCM.
|
Package lmnt is a streaming text-to-speech service backed by LMNT's HTTP "speech bytes" endpoint, which streams raw PCM. |
|
Package mem0 adds long-term memory to a jargo voice agent, backed by a mem0 server (https://github.com/mem0ai/mem0).
|
Package mem0 adds long-term memory to a jargo voice agent, backed by a mem0 server (https://github.com/mem0ai/mem0). |
|
Package minimax is a streaming text-to-speech service backed by MiniMax's T2A API.
|
Package minimax is a streaming text-to-speech service backed by MiniMax's T2A API. |
|
Package mistral provides Mistral AI's OpenAI-compatible LLM service.
|
Package mistral provides Mistral AI's OpenAI-compatible LLM service. |
|
Package nebius provides Nebius AI Studio's OpenAI-compatible LLM service.
|
Package nebius provides Nebius AI Studio's OpenAI-compatible LLM service. |
|
Package neuphonic is a streaming text-to-speech service backed by Neuphonic's TTS WebSocket.
|
Package neuphonic is a streaming text-to-speech service backed by Neuphonic's TTS WebSocket. |
|
Package novita provides Novita AI's OpenAI-compatible LLM service.
|
Package novita provides Novita AI's OpenAI-compatible LLM service. |
|
Package nvidia provides NVIDIA services: an NVIDIA NIM OpenAI-compatible LLM (NewLLM), a Riva streaming speech-to-text service (NewSTT), and a Riva streaming text-to-speech service (NewTTS).
|
Package nvidia provides NVIDIA services: an NVIDIA NIM OpenAI-compatible LLM (NewLLM), a Riva streaming speech-to-text service (NewSTT), and a Riva streaming text-to-speech service (NewTTS). |
|
internal/rivapb
Package rivapb holds the generated gRPC clients for the subset of the NVIDIA Riva speech API the streaming ASR and TTS services use.
|
Package rivapb holds the generated gRPC clients for the subset of the NVIDIA Riva speech API the streaming ASR and TTS services use. |
|
Package ollama provides a client for a local Ollama server through its OpenAI-compatible LLM endpoint.
|
Package ollama provides a client for a local Ollama server through its OpenAI-compatible LLM endpoint. |
|
openai
|
|
|
chat
Package chat provides OpenAI's LLM, STT and TTS services, plus the OpenAI-compatible LLM base that other providers (Groq, Together, Fireworks and the rest) wrap with their own base URL, key and default model.
|
Package chat provides OpenAI's LLM, STT and TTS services, plus the OpenAI-compatible LLM base that other providers (Groq, Together, Fireworks and the rest) wrap with their own base URL, key and default model. |
|
realtime
Package realtime is a speech-to-speech service built on OpenAI's Realtime API.
|
Package realtime is a speech-to-speech service built on OpenAI's Realtime API. |
|
responses
Package responses provides OpenAI's Responses API as an LLM service, in two forms.
|
Package responses provides OpenAI's Responses API as an LLM service, in two forms. |
|
Package openrouter provides OpenRouter's OpenAI-compatible LLM service, a gateway to many models behind one API.
|
Package openrouter provides OpenRouter's OpenAI-compatible LLM service, a gateway to many models behind one API. |
|
Package perplexity provides Perplexity's OpenAI-compatible LLM service.
|
Package perplexity provides Perplexity's OpenAI-compatible LLM service. |
|
Package piper is a text-to-speech provider for a local Piper HTTP server (python -m piper.http_server).
|
Package piper is a text-to-speech provider for a local Piper HTTP server (python -m piper.http_server). |
|
Package qwen provides Alibaba's Qwen LLM over the DashScope OpenAI-compatible endpoint.
|
Package qwen provides Alibaba's Qwen LLM over the DashScope OpenAI-compatible endpoint. |
|
Package resembleai is a streaming text-to-speech service backed by Resemble AI's WebSocket.
|
Package resembleai is a streaming text-to-speech service backed by Resemble AI's WebSocket. |
|
Package rime is a streaming text-to-speech service backed by Rime's HTTP API.
|
Package rime is a streaming text-to-speech service backed by Rime's HTTP API. |
|
Package sambanova provides SambaNova Cloud's OpenAI-compatible LLM service.
|
Package sambanova provides SambaNova Cloud's OpenAI-compatible LLM service. |
|
Package sarvam provides Sarvam's OpenAI-compatible LLM plus its WebSocket streaming text-to-speech and speech-to-text services for Indian languages.
|
Package sarvam provides Sarvam's OpenAI-compatible LLM plus its WebSocket streaming text-to-speech and speech-to-text services for Indian languages. |
|
Package smallest is a streaming text-to-speech service backed by Smallest AI's Waves WebSocket.
|
Package smallest is a streaming text-to-speech service backed by Smallest AI's Waves WebSocket. |
|
Package soniox provides Soniox's real-time speech services over its WebSocket APIs.
|
Package soniox provides Soniox's real-time speech services over its WebSocket APIs. |
|
Package speechmatics provides Speechmatics' real-time streaming speech-to-text over its WebSocket API.
|
Package speechmatics provides Speechmatics' real-time streaming speech-to-text over its WebSocket API. |
|
Package together provides Together AI's OpenAI-compatible LLM service and its streaming speech-to-text and text-to-speech services.
|
Package together provides Together AI's OpenAI-compatible LLM service and its streaming speech-to-text and text-to-speech services. |
|
Package whispercpp is a speech-to-text provider for a local whisper.cpp server.
|
Package whispercpp is a speech-to-text provider for a local whisper.cpp server. |
|
xai
|
|
|
grok
Package grok provides xAI's (Grok) services: an OpenAI-compatible LLM, real-time streaming speech-to-text, and text-to-speech in both a streaming WebSocket and a batch HTTP form.
|
Package grok provides xAI's (Grok) services: an OpenAI-compatible LLM, real-time streaming speech-to-text, and text-to-speech in both a streaming WebSocket and a batch HTTP form. |
|
realtime
Package realtime is a speech-to-speech service built on xAI's Realtime API.
|
Package realtime is a speech-to-speech service built on xAI's Realtime API. |
|
Package xtts provides text-to-speech via a self-hosted Coqui XTTS streaming server (https://github.com/coqui-ai/xtts-streaming-server).
|
Package xtts provides text-to-speech via a self-hosted Coqui XTTS streaming server (https://github.com/coqui-ai/xtts-streaming-server). |
Click to show internal directories.
Click to hide internal directories.