ComfyUI nodes for Fish Audio Drama 3 text-to-speech with voice cloning, multi-speaker dialogue and inline cues, plus native Qwen3-ASR transcription.
165+14 this week21PythonGPL-3.0Updated 14 days ago
aliyun/alibabacloud-bailian-speech-demo
Sample code showing how to call Alibaba Cloud Bailian speech models for speech recognition, speech synthesis, and voice chat.
- Stars
- 429
- Forks
- 58
- Open issues
- 3
- Last commit
- 5 days ago
What is it?
This repository is a collection of sample code for calling Alibaba Cloud Bailian (Model Studio) speech models through the DashScope SDK. It covers speech-to-text with Qwen-Audio-3.0-ASR and Fun-ASR, text-to-speech with Qwen-Audio-3.0-TTS and CosyVoice, voice cloning, and music generation from prompts or lyrics.
Beyond basic recognition and synthesis, the samples show how to combine speech models with large language models for video chat, voice conversation, audio summarization and Q&A, and speech translation. Examples include streaming recognition with hotword and context support, asynchronous transcription of long recordings with speaker separation, and WebSocket-based real-time voice dialogue.
Each sample lives in its own directory with its own run instructions and dependencies. Setup requires an Alibaba Cloud account, a Bailian API key, and the DashScope SDK. The code is released under the MIT license.
Key features
- 01Speech recognition with Qwen-Audio-3.0-ASR and Fun-ASR, including streaming and file transcription
- 02Text-to-speech with instruction control over voice style, dialect, and emotion
- 03Voice cloning and synthesis with a cloned voice
- 04Music generation from prompts or custom lyrics
- 05Real-time voice dialogue over WebSocket with function calling
Use cases
- Adding real-time captions or transcription to meetings and live streams
- Building customer service voice bots with cloned or styled voices
- Batch transcribing and analyzing call or meeting recordings
- Generating narration or multilingual voiceovers from text or LLM output
In collections
Topics
FAQ
- What is alibabacloud-bailian-speech-demo?
- Sample code showing how to call Alibaba Cloud Bailian speech models for speech recognition, speech synthesis, and voice chat. This repository is a collection of sample code for calling Alibaba Cloud Bailian (Model Studio) speech models through the DashScope SDK. It covers speech-to-text with Qwen-Audio-3.0-ASR and Fun-ASR, text-to-speech with Qwen-Audio-3.0-TTS and CosyVoice, voice cloning, and music generation from prompts or lyrics.
- Is alibabacloud-bailian-speech-demo free to use? What license does it have?
- alibabacloud-bailian-speech-demo is open source under the MIT license. Check the license terms before using it in commercial products.
- Is alibabacloud-bailian-speech-demo still maintained?
- Actively maintained. The last commit to alibabacloud-bailian-speech-demo was on Nov 2, 2026.
- What can I use alibabacloud-bailian-speech-demo for?
- Adding real-time captions or transcription to meetings and live streams Building customer service voice bots with cloned or styled voices Batch transcribing and analyzing call or meeting recordings Generating narration or multilingual voiceovers from text or LLM output
- Where can I get alibabacloud-bailian-speech-demo?
- The source code and installation instructions are on GitHub: https://github.com/aliyun/alibabacloud-bailian-speech-demo
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
Open-source voice AI family from Microsoft, with long-form speech recognition (ASR), multi-speaker text-to-speech (TTS), and real-time streaming TTS models.
56.7K+1.6K this week6.4KPythonMITUpdated last month
Open-source text-to-speech system with voice cloning, natural-language emotion control and multi-speaker generation, built on LLM-style models.
33.6K+100 this week2.9KPythonOtherUpdated 5 days ago
Python library that turns text, generators, and LLM token streams into speech with low latency, across many local and cloud TTS engines.
4.1K415PythonMITWell maintainedUpdated yesterday
A VITS2-based text-to-speech project that adds multilingual BERT to improve prosody and pronunciation in synthesized speech.
8.8K1.3KPythonAGPL-3.0Updated 5 days ago
NVIDIA's open-source toolkit for building, fine-tuning and deploying speech AI models, covering speech recognition (ASR), text-to-speech (TTS) and speech LLMs.
18.7K+50 this week3.7KPythonApache-2.0Updated yesterday