Text to Speech
Text to Speech is the voice of a voice agent with any speech synthesis provider in NappAI: you choose Provider and the agent speaks exactly as with that provider’s own component, such as ElevenLabs TTS or OpenAI TTS.
The difference is that switching provider does not mean switching node or rewiring the agent: you change it in the field, and the node remembers the credential of every provider you already set up.
It plugs into the TTS connector of the Voice Agent node.
When to use it
- You want to hear the same conversation with voices from several providers before choosing one.
- You want to be able to move from a paid voice to a local one, or the other way round, without touching the rest of the flow.
If the provider will not change, use its own component: it shows all its fields and its list of voices directly.
Configuration
| Field | What it does |
|---|---|
| Provider | The voice provider. Default: OpenAI. The options are ElevenLabs, Cartesia, OpenAI, Gemini, Azure, Deepgram, Inworld and the local Kokoro, Piper, Supertonic and Pocket. Choose it first: when you change it, the node asks for that provider’s credential. |
| Credential (required if the provider uses one) | The credential of the chosen provider. The list only shows that provider’s credentials. Kokoro, Piper, Supertonic and Pocket need none. See Credentials. |
| Voice | The voice. Each provider has its own: when you switch provider it is filled with that provider’s default voice. You can type any voice name or ID of the provider. |
| Model | The provider’s speech model. When you switch provider it is filled with that provider’s default. |
| Speed | The pace of the voice. 1.0 is its natural pace. Only with the providers that support it. |
Advanced options
| Field | What it does |
|---|---|
| Instructions | How the voice should sound, in words, for example «warm and unhurried». Only with the providers that support it, such as OpenAI. |
| Provider Settings | Other fields of the provider’s own component, each with its own name. Fields the provider does not have are ignored. |
| Credentials by Provider | The credential the node remembers for each provider. It fills itself in when you choose a credential. |
Each provider’s voices and options are explained on its page, for example in ElevenLabs TTS.
Output
The TTS output holds the voice settings. It plugs into the TTS connector of the Voice Agent node, or into Fallback TTS if you turn on Fallback Engines and want to use it as a backup.
Example
A travel agency wants to choose its agent’s voice by listening to several providers.
- Connect Text to Speech to the TTS connector of the Voice Agent.
- Choose
ElevenLabs, its credential and a voice, and talk to the agent in the playground. - Switch to
Kokoro, which needs no credential, choose a voice and repeat. - Keep the one people like best and deploy the flow.
Good practices
- When you switch provider, check Voice: the previous provider’s voice does not exist in the new one.
- The voice agent answers calls with the deployed version of the flow: after switching provider, deploy so that real calls use it.
- The spend is recorded on the chosen provider’s credential.
Related components
- Voice Agent: the node this component plugs into.
- Speech to Text: the agent’s hearing, also with a provider to choose.
- Language Model: the agent’s model, also with a provider to choose.