Camb.ai

OverviewCopy Anchor Link

CambTTSService posts each sentence to Camb.ai's tts-stream endpoint and pushes the streamed 16-bit PCM, kept aligned to whole samples. Models: mars-flash (fast, 22.05 kHz, the default), mars-pro (high quality, 48 kHz) and mars-instruct (22.05 kHz, takes instructions for tone and style).

InstallationCopy Anchor Link

bun add @pipedog/camb

import { CambTTSService } from "@pipedog/camb/tts";

PrerequisitesCopy Anchor Link

• A Camb.ai account and an API key.
• Pass the key as apiKey. The examples read it from CAMB_API_KEY.

ConfigurationCopy Anchor Link

SettingsCopy Anchor Link

Runtime-updatable settings, passed as settings: new CambTTSService.Settings({...}) (CambTTSSettings). Any setting you leave out keeps the default below.

UsageCopy Anchor Link

import { CambTTSService } from "@pipedog/camb/tts";
import { TTSUpdateSettingsFrame } from "@pipedog/core/frames/frames";

// mars-flash (22.05 kHz) is the default; mars-pro renders at 48 kHz.
const tts = new CambTTSService({
  apiKey: process.env.CAMB_API_KEY ?? "",
  settings: new CambTTSService.Settings({ model: "mars-pro", voice: 147320 }),
});

Change settings mid-call with a TTSUpdateSettingsFrame:

// Queue it on the worker, or push it from a processor upstream of the service.
const update = new TTSUpdateSettingsFrame({
  delta: new CambTTSService.Settings({ voice: 12345 }),
});

NotesCopy Anchor Link

• Without a sampleRate, the service uses the model's: 22050 Hz for mars-flash and mars-instruct, 48000 Hz for mars-pro. A sampleRate that differs from the model's logs a warning.
• Text over 3000 characters is truncated.
• timeout (60 seconds by default, the minimum Camb.ai recommends) limits the wait for the response and the wait for each chunk of audio.

Runtime notesCopy Anchor Link

• Upstream uses Camb's Python SDK. That SDK is a thin client over one endpoint, so this port sends the same request (POST /tts-stream with an x-api-key header) with the global fetch, which works on Bun, Node, Deno and Cloudflare Workers. baseUrl and fetch are not upstream options.
• The deprecated params (InputParams), voiceId and model options are not ported. Use settings.
• Upstream has no Camb.ai tests. Ours run against a local fake server, not against Camb.ai itself.

Generated from pipecat.runtimes and pipecat.compat in packages/camb/package.json: ✅ means the compat smoke test passes on that runtime.