Speech-to-text
Speech-to-text
Transcribe the user's speech into TranscriptionFrames.
A speech-to-text service takes the user's audio frames and pushes TranscriptionFrames (and InterimTranscriptionFrames while the user speaks).
| Provider | Classes | Package | Status |
|---|---|---|---|
| AssemblyAI | AssemblyAISTTService, AssemblyAISyncSTTService | @pipedog/assemblyai | Ported |
| Gladia | GladiaSTTService | @pipedog/gladia | Ported |
| Speechmatics | SpeechmaticsSTTService | @pipedog/speechmatics | Ported |
| Soniox | SonioxSTTService | @pipedog/soniox | Ported |
| Deepgram | DeepgramSTTService, DeepgramFluxSTTService | @pipedog/deepgram | Ported |
| Cloudflare Workers AI | WorkersAIFluxSTTService, WorkersAINova3STTService, WorkersAIWhisperSTTService | @pipedog/cloudflare | Ported |
| OpenAI | OpenAISTTService, OpenAIRealtimeSTTService | @pipedog/openai | Ported |
GoogleSTTService, GeminiSTTService | @pipedog/google | Ported | |
| Cartesia | CartesiaSTTService, CartesiaTurnsSTTService | @pipedog/cartesia | Ported |
| ElevenLabs | ElevenLabsSTTService, ElevenLabsRealtimeSTTService | @pipedog/elevenlabs | Ported |
| AWS Transcribe | AWSTranscribeSTTService | @pipedog/aws | Ported |
| AWS SageMaker (bidi client) | SageMakerBidiClient | @pipedog/aws | Ported |
| Azure Speech | AzureSTTService | @pipedog/azure | Ported |
| Whisper | WhisperSTTService, WhisperSTTServiceMLX, BaseWhisperSTTService | @pipedog/whisper | Ported |
| Moonshine (local) | MoonshineSTTService | @pipedog/moonshine | Ported |
| FunASR SenseVoice (local) | FunASRSTTService | @pipedog/funasr | Ported |
| Groq | GroqSTTService | @pipedog/groq | Ported |
| Mistral | MistralSTTService | @pipedog/mistral | Ported |
| Together AI | TogetherSTTService | @pipedog/together | Ported |
| xAI | XAISTTService | @pipedog/xai | Ported |
| Sarvam AI | SarvamSTTService, SarvamRealtimeSTTService | @pipedog/sarvam | Ported |
| Smallest AI | SmallestSTTService | @pipedog/smallest | Ported |
| Gradium | GradiumSTTService | @pipedog/gradium | Ported |
| Meta | MetaSTTService | @pipedog/meta | Ported |
| Zoom AI | ZoomAISTTService | @pipedog/zoom-ai | Ported |
| NVIDIA Riva | NvidiaSTTService, NvidiaSegmentedSTTService | Coming soon |
Pipecat's speech-to-text 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).