
by Fish Audio
Fish Audio is a voice AI platform for text-to-speech, voice cloning and speech-to-text, available in the browser, through an API and in a Python SDK.
APIFreemium
Step 1: Create a Fish Audio account and verify your email.
Step 2: Generate an API key; it is shown once, so store it securely.
Step 3: Save the key as an environment variable and install the Python SDK.
Step 4: Send a text-to-speech request and save the returned audio file.
Step 5: Add a voice ID to use a different voice, or create your own voice model.
Yes. Fish Audio provides compatibility endpoints for the OpenAI, OpenRouter, ElevenLabs and Groq SDKs. You change the base URL and API key and the code keeps working.
No. Generating audio, cloning voices and building projects can be done in the browser.
Yes. Audio can be streamed as it generates, and the SDK guide covers streaming LLM tokens to speech as they arrive.
The quickstart lists common causes such as an invalid API key or no API credit for the model you called. On a zero balance, use the free-to-use model.
Speechmatics APISpeechmatics API applies AI to speech recognition API for realtime and batch transcription across accents, languages, and enterprise audio.
Gemini TranscribeGemini Transcribe is Google's speech-to-text model in the Gemini API, with real-time streaming and pre-recorded audio transcription. It returns cleaned, formatted text with speaker labels and word timestamps.