Text-to-speech
Text-to-speech
Turn the bot's text into audio frames.
A text-to-speech service takes the bot's text frames and pushes audio frames, with word timestamps where the provider sends them.
| Provider | Classes | Package | Status |
|---|---|---|---|
| OpenAI | OpenAITTSService | @pipedog/openai | Ported |
GoogleTTSService, GoogleHttpTTSService, GeminiTTSService | @pipedog/google | Ported | |
| Deepgram | DeepgramTTSService, DeepgramHttpTTSService, DeepgramFluxTTSService | @pipedog/deepgram | Ported |
| Cloudflare Workers AI | WorkersAIAuraTTSService, WorkersAIAuraHttpTTSService, WorkersAIMeloTTSService | @pipedog/cloudflare | Ported |
| Speechmatics | SpeechmaticsTTSService | @pipedog/speechmatics | Ported |
| Soniox | SonioxTTSService | @pipedog/soniox | Ported |
| Cartesia | CartesiaTTSService, CartesiaHttpTTSService | @pipedog/cartesia | Ported |
| ElevenLabs | ElevenLabsTTSService, ElevenLabsHttpTTSService, ElevenLabsDialogueTTSService | @pipedog/elevenlabs | Ported |
| Groq | GroqTTSService | @pipedog/groq | Ported |
| Mistral | MistralTTSService | @pipedog/mistral | Ported |
| Together AI | TogetherTTSService | @pipedog/together | Ported |
| xAI | XAITTSService, XAIHttpTTSService | @pipedog/xai | Ported |
| Sarvam AI | SarvamTTSService, SarvamHttpTTSService | @pipedog/sarvam | Ported |
| Smallest AI | SmallestTTSService | @pipedog/smallest | Ported |
| Gradium | GradiumTTSService | @pipedog/gradium | Ported |
| Inworld | InworldTTSService, InworldHttpTTSService | @pipedog/inworld | Ported |
| AWS Polly | AWSPollyTTSService | @pipedog/aws | Ported |
| Azure Speech | AzureTTSService, AzureHttpTTSService | @pipedog/azure | Ported |
| Kokoro (local) | KokoroTTSService | @pipedog/kokoro | Ported |
| Piper | PiperTTSService, PiperHttpTTSService | @pipedog/piper | Ported |
| Pocket TTS (local) | PocketTTSService | @pipedog/pocket-tts | Ported |
| Rime | RimeTTSService, RimeHttpTTSService, RimeV1TTSService | @pipedog/rime | Ported |
| Fish Audio | FishAudioTTSService | @pipedog/fish | Ported |
| Hume | HumeTTSService | @pipedog/hume | Ported |
| Neuphonic | NeuphonicTTSService, NeuphonicHttpTTSService | @pipedog/neuphonic | Ported |
| Speechify | SpeechifyHttpTTSService | @pipedog/speechify | Ported |
| MiniMax | MiniMaxHttpTTSService | @pipedog/minimax | Ported |
| Resemble AI | ResembleAITTSService | @pipedog/resembleai | Ported |
| Camb.ai | CambTTSService | @pipedog/camb | Ported |
| Async | AsyncAITTSService, AsyncAIHttpTTSService | @pipedog/asyncai | Ported |
| Bland | BlandTTSService, BlandHttpTTSService | @pipedog/bland | Ported |
| AssemblyAI | AssemblyAITTSService | @pipedog/assemblyai | Ported |
| NVIDIA Riva | NvidiaTTSService | Coming soon |
Pipecat's text-to-speech reference lists every upstream provider. Those not in this table are on Other upstream providers.
pipedog is an unofficial community TypeScript port of Pipecat. It is not affiliated with or endorsed by Daily or the Pipecat project.
Portions adapted from the Pipecat documentation, Copyright (c) 2024–2025 Daily, BSD-2-Clause (see apps/docs/LICENSE-pipecat-docs).