> For clean Markdown of any page, append .md to the page URL. > For a complete documentation index, see https://docs.jambonz.org/llms.txt. > For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.jambonz.org/_mcp/server. # Realtime voice API A **Realtime voice API** agent hands the whole voice loop to one vendor: speech recognition, turn-taking, barge-in, the model and the voice all run inside the vendor's session. You choose the vendor, the model and the voice. It gives the lowest latency and the most natural turn-taking, with one vendor to configure. jambonz runs it with the [llm verb](/verbs/verbs/llm). You write the prompt and add tools and knowledge in Studio, as for a pipeline agent. The vendor, model and voice are in the agent's **Model & voice** section. ## Vendors and credentials Each vendor needs its own credential in your jambonz account, added in the jambonz portal under **LLM Services**, on the **Speech-to-speech** tab. It is a credential of its own, separate from any language model or speech credential for the same vendor. | Vendor | Starting model | Starting voice | Notes | | ------------------------ | --------------- | -------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------- | | **OpenAI Realtime** | `gpt-realtime` | `marin` | Also suggests `gpt-realtime-mini`. | | **OpenAI GPT-Live** | `gpt-live-1` | `marin` | Tool calls, transfers and hangups run on a separate **Model for delegated work** (starts on `gpt-6.1-terra`). | | **Rime Prism** | none | `astra` | No model choice. Four voices: `astra`, `aurora`, `brando` and `wawona`. English only. | | **Deepgram Voice Agent** | `gpt-4.1-mini` | `flux-kit-en` | Deepgram listens (Flux for English, Nova-3 otherwise), runs the LLM and speaks with a Flux or Aura voice, and bills all three to your Deepgram account. | | **Ultravox** | `ultravox-v0.7` | `Olivia` | Ultravox has many voices; Studio suggests a few English ones. | You choose the vendor in the **New agent** dialog. If the account has no credential for it yet, you can still build the agent and add the credential later. ## Model & voice | Field | What it is | | ---------------------------- | -------------------------------------------------------------------------------------------------------------------- | | **Vendor** | One of the five vendors above. Switching vendor clears the credential and starts from that vendor's model and voice. | | **Credential** | The vendor's credential from your jambonz account. When you have more than one, the label picks which. | | **Model** | The vendor's model. For Deepgram Voice Agent this is **LLM (managed by Deepgram)**. Not shown for Rime Prism. | | **Voice** | The vendor's voice. | | **Language** | The language of the conversation (`en-US` to start). | | **Model for delegated work** | OpenAI GPT-Live only: the model its tool calls, transfers and hangups run on. | For every field you can pick a suggestion or type any model, voice or language code the vendor accepts. ### Options The **Options** fold takes extra vendor settings as JSON: * **OpenAI Realtime** and **OpenAI GPT-Live**: any key from the OpenAI section of the [llm verb](/verbs/verbs/llm) docs, for example `turn_detection` or `temperature`. Studio asks OpenAI Realtime to transcribe the caller, so the call history has the caller's words; set `input_audio_transcription` here to change that. * **Rime Prism**: only `turn_detection` (`interrupt_response`, `eagerness`, `prism_end_of_turn_timeout_ms`) and `truncation`. Anything else is left out. * **Deepgram Voice Agent**: `listen`, `think` and `speak` are merged into Deepgram's providers; `mip_opt_out`, `tags` and `flags` go in the settings. * **Ultravox**: any setting of an Ultravox call, such as `temperature`, `vadSettings` or `inactivityMessages`. Do not put the prompt, tools or voice here; Studio adds them. For Rime Prism, Deepgram Voice Agent and Ultravox, Studio notes any option it leaves out. ### Handled by the vendor Speech recognition, turn detection, barge-in, the voice and noise handling happen inside the vendor's session. The pipeline's turn-taking and interruption settings do not appear in the **Conversation** section for these agents; tune them through the vendor's options. ### Greeting An **OpenAI Realtime** agent always speaks first. If its greeting is set to wait for the caller, Studio notes that it will not wait. Rime Prism and OpenAI GPT-Live can wait for the caller. ## Studio's own lines On a warm transfer, Studio speaks a brief to the person who answers ("Brief the person first", in **Transfer & hangup**). The vendor's voice is inside its session, so Studio speaks the brief itself, with a text-to-speech credential from your account. The secure detour's message is different: a Realtime voice API agent says that line itself, in its own voice. When the agent has a warm transfer with a brief, **Model & voice** shows **Voice for Studio's own lines**: * **Speak them in the agent's voice**: shown when the vendor also sells the agent's voice as text-to-speech. Turn it on and Studio speaks the brief in the same voice as the agent: | Vendor | When it is offered | Text-to-speech credential needed | | -------------------- | --------------------------------------------------- | ---------------------------------------------------------- | | Deepgram Voice Agent | a Flux voice (`flux-…`) or an Aura voice (`aura-…`) | Deepgram Flux for a Flux voice, Deepgram for an Aura voice | | Rime Prism | the `astra` or `wawona` voice | RimeLabs | Studio offers only credentials of that vendor, and uses the agent's voice. If the chosen credential is from another vendor, Studio notes that it needs one from the agent's vendor. * Otherwise, choose a text-to-speech credential and a voice for Studio's lines. OpenAI Realtime, OpenAI GPT-Live and Ultravox voices are not sold as text-to-speech, so for those the brief is spoken in a voice you choose here. If no voice is chosen, Studio notes that it has no voice to speak the brief with. The transfer's **Brief for the person** field in **Transfer & hangup** shows which voice will speak it, with a link back here. ## Next * [Cascaded voice pipeline](/agent-studio/agent-types/cascaded-pipeline): choose each stage's vendor yourself * [Connected agent](/agent-studio/agent-types/connected-agent): an agent built on Dialogflow CES or ElevenLabs