Doubao connector for Okou
Connect Volcengine Doubao (豆包语音) for Mandarin-first text-to-speech, speech recognition, and voice cloning.
Voice & audio · Doubao API Key
Use Doubao in Okou
Doubao (Volcengine 豆包语音) API for Chinese-first text-to-speech, speech recognition, voice cloning, and end-to-end realtime voice.
Once connected, supported Doubao actions can become steps in a reusable workflow alongside the other services your team uses. Run the workflow once, on a schedule, or when an event starts it.
What you can do with Doubao
- Synthesise speech (HTTP, streaming chunked)
- Synthesise speech (SSE)
- Transcribe an audio file (async)
- Streaming ASR (WebSocket)
- Clone a voice
- SSML
- Speaker ↔ Resource-Id table
- Reliable default speakers
How the Doubao connector works
A connected service becomes one permissioned step in the work you hand off.
- 1
Connect Doubao
Choose Doubao API Key.
- 2
Choose the work
Use only the supported actions your workflow needs.
- 3
Run it your way
Start it once, schedule it, or attach an event trigger.
Connect Doubao securely
Use the connection method that fits your account and grant only the access the workflow needs.
- Doubao API Key
Connector access is controlled per service and per action, so a workflow does not need broader access than the work you ask it to do.
Doubao connector questions
- What can Okou do with Doubao?
- Connect Volcengine Doubao (豆包语音) for Mandarin-first text-to-speech, speech recognition, and voice cloning. Documented actions include: Synthesise speech (HTTP, streaming chunked). Synthesise speech (SSE).
- How do I connect Doubao to Okou?
- Connect Doubao using Doubao API Key. The connection controls which supported actions a workflow can use.
- Can Doubao run in an automated workflow?
- Yes. After it is connected, supported Doubao actions can run in reusable Okou workflows on demand, on a schedule, or from an event trigger.
More voice & audio connectors
Explore other connectors in the same product category.
ElevenLabs
Connect your ElevenLabs account to generate speech, clone voices, manage audio projects, and access sound effects.
Deepgram
Connect Deepgram to transcribe audio, analyze text, generate speech, inspect models, and review project usage.
Fish Audio
Connect Fish Audio to synthesize and transcribe audio, design and manage voice models, and inspect account usage.
