agent-ttsUse a cloud voice
Use ElevenLabs, OpenAI, or Azure instead of the OS speech engine.
Switch the backend to cloud, pick a provider and voice, and keep the API key in the environment.
tts backend cloud
tts cloud provider elevenlabs
tts cloud voice 21m00Tcm4TlvDq8ikWAMEach utterance is synthesized over HTTPS and played locally (afplay on macOS; ffplay / mpg123 / aplay / paplay on Linux; PowerShell media APIs on Windows).
| Provider | provider | Voice id example | Key |
|---|---|---|---|
| ElevenLabs | elevenlabs | 21m00Tcm4TlvDq8ikWAM (Rachel) | ELEVENLABS_API_KEY |
| OpenAI | openai | alloy, nova, … | OPENAI_API_KEY |
| Azure | azure | en-US-JennyNeural | AZURE_SPEECH_KEY plus tts cloud region |
tts voices lists ElevenLabs voices when a key is set. OpenAI tts wpm maps to the API speed parameter.
Prefer the environment variable over tts cloud key so the key never lands in config.json. A missing key or failed request stays silent for that turn - check ~/.agent-tts/debug.log.
On macOS, quality of the local backend comes from voices in System Settings → Accessibility → Spoken Content. Siri voices are not selectable by name through say. Leave prose_voice null and set the system voice to try that path.