Speech-to-text, text-to-speech, voice
Text-to-speech, voice cloning, dubbing, and an official MCP server over the audio platform
Speech recognition, diarization, and audio intelligence models via API
Sonic low-latency text-to-speech and voice models built for realtime agents
Speech-to-text and Aura text-to-speech with streaming, sub-200ms first audio
Whisper and gpt-4o-transcribe endpoints for transcription and translation
Text-to-speech with voice cloning and streaming output
Same query as JSON: /api/v1/services?category=hear-speak&auth_method=api-keyAdd to Claude Code:claude mcp add botfriendly …