# Fish Audio

> Documentation for Fish Audio APIs, SDKs, models, voice cloning, real-time streaming, and self-hosting.

## Docs

- [Create Model](https://hanabiaiinc-docs-concurrency-qpm-rate-limits.mintlify.site/api-reference/endpoint/model/create-model.md): Create a new voice model
- [Delete Model](https://hanabiaiinc-docs-concurrency-qpm-rate-limits.mintlify.site/api-reference/endpoint/model/delete-model.md): Delete an existing model
- [Get Model](https://hanabiaiinc-docs-concurrency-qpm-rate-limits.mintlify.site/api-reference/endpoint/model/get-model.md): Get details of a specific model
- [List Models](https://hanabiaiinc-docs-concurrency-qpm-rate-limits.mintlify.site/api-reference/endpoint/model/list-models.md): Get a list of all models
- [Update Model](https://hanabiaiinc-docs-concurrency-qpm-rate-limits.mintlify.site/api-reference/endpoint/model/update-model.md): Update an existing model
- [Speech to Text](https://hanabiaiinc-docs-concurrency-qpm-rate-limits.mintlify.site/api-reference/endpoint/openapi-v1/speech-to-text.md): Transcribe audio to text
- [Text to Speech](https://hanabiaiinc-docs-concurrency-qpm-rate-limits.mintlify.site/api-reference/endpoint/openapi-v1/text-to-speech.md): Convert text to speech
- [Text to Speech Stream with Timestamps](https://hanabiaiinc-docs-concurrency-qpm-rate-limits.mintlify.site/api-reference/endpoint/openapi-v1/text-to-speech-stream-with-timestamps.md): Stream generated speech with timestamp alignment snapshots
- [Voice Design](https://hanabiaiinc-docs-concurrency-qpm-rate-limits.mintlify.site/api-reference/endpoint/openapi-v1/voice-design.md): Generate candidate voices from a prompt
- [Get API Credit](https://hanabiaiinc-docs-concurrency-qpm-rate-limits.mintlify.site/api-reference/endpoint/wallet/get-api-credit.md): Get current API credit balance
- [Get User Package](https://hanabiaiinc-docs-concurrency-qpm-rate-limits.mintlify.site/api-reference/endpoint/wallet/get-user-package.md): Get current user premium information
- [WebSocket TTS Streaming](https://hanabiaiinc-docs-concurrency-qpm-rate-limits.mintlify.site/api-reference/endpoint/websocket/tts-live.md): Real-time text-to-speech streaming via WebSocket
- [Errors](https://hanabiaiinc-docs-concurrency-qpm-rate-limits.mintlify.site/api-reference/errors.md): HTTP status codes, the error response shape, and how to handle them in any language
- [Introduction](https://hanabiaiinc-docs-concurrency-qpm-rate-limits.mintlify.site/api-reference/introduction.md): How to use the Fish Audio API
- [Tracing & Performance Analysis](https://hanabiaiinc-docs-concurrency-qpm-rate-limits.mintlify.site/api-reference/observability.md): Correlate Fish Audio inference spans with your own distributed traces
- [JavaScript SDK Reference](https://hanabiaiinc-docs-concurrency-qpm-rate-limits.mintlify.site/api-reference/sdk/javascript/api-reference.md): Complete reference for Fish Audio JavaScript SDK
- [Client](https://hanabiaiinc-docs-concurrency-qpm-rate-limits.mintlify.site/api-reference/sdk/python/client.md)
- [Core](https://hanabiaiinc-docs-concurrency-qpm-rate-limits.mintlify.site/api-reference/sdk/python/core.md)
- [Exceptions](https://hanabiaiinc-docs-concurrency-qpm-rate-limits.mintlify.site/api-reference/sdk/python/exceptions.md)
- [Overview](https://hanabiaiinc-docs-concurrency-qpm-rate-limits.mintlify.site/api-reference/sdk/python/overview.md): Fish Audio Python SDK for text-to-speech and voice cloning
- [Resources](https://hanabiaiinc-docs-concurrency-qpm-rate-limits.mintlify.site/api-reference/sdk/python/resources.md)
- [Types](https://hanabiaiinc-docs-concurrency-qpm-rate-limits.mintlify.site/api-reference/sdk/python/types.md)
- [Utils](https://hanabiaiinc-docs-concurrency-qpm-rate-limits.mintlify.site/api-reference/sdk/python/utils.md)
- [Legacy](https://hanabiaiinc-docs-concurrency-qpm-rate-limits.mintlify.site/archive/python-sdk-legacy/index.md): Archived documentation for the legacy Session-based Python SDK
- [Contributing](https://hanabiaiinc-docs-concurrency-qpm-rate-limits.mintlify.site/contributing.md): Help improve Fish Audio and contribute to our open source projects.
- [Emotion & Expression Control](https://hanabiaiinc-docs-concurrency-qpm-rate-limits.mintlify.site/developer-guide/best-practices/emotion-control.md): Make your AI voices express emotions naturally
- [Real-time Voice Streaming](https://hanabiaiinc-docs-concurrency-qpm-rate-limits.mintlify.site/developer-guide/best-practices/real-time-streaming.md): Stream voice generation in real-time for interactive applications
- [Voice Cloning Best Practices](https://hanabiaiinc-docs-concurrency-qpm-rate-limits.mintlify.site/developer-guide/best-practices/voice-cloning.md): Simple tips to get the best voice cloning results with Fish Audio
- [Emotion Control](https://hanabiaiinc-docs-concurrency-qpm-rate-limits.mintlify.site/developer-guide/core-features/emotions.md): Add natural emotions and expressions to your AI-generated speech
- [Fine-grained Control](https://hanabiaiinc-docs-concurrency-qpm-rate-limits.mintlify.site/developer-guide/core-features/fine-grained-control.md): Advanced control over speech generation
- [Chinese Phoneme Control](https://hanabiaiinc-docs-concurrency-qpm-rate-limits.mintlify.site/developer-guide/core-features/fine-grained-control/chinese.md): Control Chinese pronunciation with tone-number pinyin
- [English Phoneme Control](https://hanabiaiinc-docs-concurrency-qpm-rate-limits.mintlify.site/developer-guide/core-features/fine-grained-control/english.md): Control English pronunciation with CMU Arpabet
- [Japanese Phoneme Control](https://hanabiaiinc-docs-concurrency-qpm-rate-limits.mintlify.site/developer-guide/core-features/fine-grained-control/japanese.md): Control Japanese pronunciation with romaji phonemes and pitch accent markers
- [Get Your API Key](https://hanabiaiinc-docs-concurrency-qpm-rate-limits.mintlify.site/developer-guide/getting-started/api-key.md): Create a Fish Audio account, generate an API key, and make your first request
- [Changelog](https://hanabiaiinc-docs-concurrency-qpm-rate-limits.mintlify.site/developer-guide/getting-started/changelog.md): Complete release history and version updates for all Fish Audio products
- [Quick Start](https://hanabiaiinc-docs-concurrency-qpm-rate-limits.mintlify.site/developer-guide/getting-started/quickstart.md): Generate your first AI voice with Fish Audio in under 5 minutes
- [LiveKit](https://hanabiaiinc-docs-concurrency-qpm-rate-limits.mintlify.site/developer-guide/integrations/livekit.md): Build real-time voice AI agents with Fish Audio and LiveKit
- [n8n](https://hanabiaiinc-docs-concurrency-qpm-rate-limits.mintlify.site/developer-guide/integrations/n8n.md): Automate workflows with Fish Audio and n8n
- [Pipecat](https://hanabiaiinc-docs-concurrency-qpm-rate-limits.mintlify.site/developer-guide/integrations/pipecat.md): Build voice AI agents with Fish Audio and Pipecat
- [Choosing a Model](https://hanabiaiinc-docs-concurrency-qpm-rate-limits.mintlify.site/developer-guide/models-pricing/choosing-a-model.md): Select the right Fish Audio model for your use case and requirements
- [Model Deprecations](https://hanabiaiinc-docs-concurrency-qpm-rate-limits.mintlify.site/developer-guide/models-pricing/deprecations.md): Track deprecated models and migration timelines for Fish Audio services
- [Models Overview](https://hanabiaiinc-docs-concurrency-qpm-rate-limits.mintlify.site/developer-guide/models-pricing/models-overview.md): Explore Fish Audio's voice generation models and their capabilities
- [Pricing & Rate Limits](https://hanabiaiinc-docs-concurrency-qpm-rate-limits.mintlify.site/developer-guide/models-pricing/pricing-and-rate-limits.md): Understand Fish Audio pricing plans, usage costs, and API rate limits
- [Agent Quickstart](https://hanabiaiinc-docs-concurrency-qpm-rate-limits.mintlify.site/developer-guide/resources/agent-quickstart.md): Build with Fish Audio using your AI coding agent — install the skill and start prompting in a minute
- [Brand Guidelines](https://hanabiaiinc-docs-concurrency-qpm-rate-limits.mintlify.site/developer-guide/resources/brand.md): Design guidelines for using Fish Audio brand assets
- [AI Coding Agents](https://hanabiaiinc-docs-concurrency-qpm-rate-limits.mintlify.site/developer-guide/resources/coding-agents.md): Install the Fish Audio skill so your coding agent writes correct SDK and API code
- [Batch-transcribe files with a language hint](https://hanabiaiinc-docs-concurrency-qpm-rate-limits.mintlify.site/developer-guide/sdk-guide/cookbook/batch-transcribe-with-language-hint.md): Loop over local audio files and transcribe each with an explicit language, collecting text and duration per file
- [Clone a voice and wait until it is ready](https://hanabiaiinc-docs-concurrency-qpm-rate-limits.mintlify.site/developer-guide/sdk-guide/cookbook/clone-and-wait-until-ready.md): Create a persistent voice from a reference clip, poll until training finishes, then synthesize with it
- [Discover and reuse a Voice Library voice](https://hanabiaiinc-docs-concurrency-qpm-rate-limits.mintlify.site/developer-guide/sdk-guide/cookbook/discover-library-voice.md): Search the public Voice Library by title, pick a result, and synthesize speech with it as your reference_id
- [Instant voice cloning](https://hanabiaiinc-docs-concurrency-qpm-rate-limits.mintlify.site/developer-guide/sdk-guide/cookbook/instant-voice-cloning.md): Clone a voice on the fly from a short reference clip, with no model to manage
- [One-shot vs persistent cloning: pick the right approach](https://hanabiaiinc-docs-concurrency-qpm-rate-limits.mintlify.site/developer-guide/sdk-guide/cookbook/oneshot-vs-persistent-cloning.md): Choose between instant per-request cloning and a saved, reusable voice model
- [Realtime: LLM tokens → speech](https://hanabiaiinc-docs-concurrency-qpm-rate-limits.mintlify.site/developer-guide/sdk-guide/cookbook/realtime-llm-to-speech.md): Pipe a streaming LLM response straight into speech over a WebSocket as tokens arrive
- [Stream TTS to a file](https://hanabiaiinc-docs-concurrency-qpm-rate-limits.mintlify.site/developer-guide/sdk-guide/cookbook/streaming-to-file.md): Generate long audio and write it to disk chunk-by-chunk, without buffering it all in memory
- [Telephony-grade audio (8 kHz) for IVR and phone](https://hanabiaiinc-docs-concurrency-qpm-rate-limits.mintlify.site/developer-guide/sdk-guide/cookbook/telephony-8khz-audio.md): Generate 8 kHz mono WAV/PCM that matches the narrowband sample rate phone networks expect for IVR and call-center playback
- [Transcribe audio to SRT/VTT captions](https://hanabiaiinc-docs-concurrency-qpm-rate-limits.mintlify.site/developer-guide/sdk-guide/cookbook/transcribe-to-captions.md): Transcribe audio with timestamps and write valid SRT and WebVTT caption files from the segments
- [Build a voice agent loop: speech in, reply, speech out](https://hanabiaiinc-docs-concurrency-qpm-rate-limits.mintlify.site/developer-guide/sdk-guide/cookbook/voice-agent-loop.md): Transcribe an utterance, generate a reply with your own LLM, and stream that reply back out as speech
- [Authentication](https://hanabiaiinc-docs-concurrency-qpm-rate-limits.mintlify.site/developer-guide/sdk-guide/python/authentication.md): Configure API authentication for the Fish Audio Python SDK
- [Errors & Retries](https://hanabiaiinc-docs-concurrency-qpm-rate-limits.mintlify.site/developer-guide/sdk-guide/python/errors.md): Exception types, retry strategy, and timeouts in the Fish Audio Python SDK
- [SDK Quickstart](https://hanabiaiinc-docs-concurrency-qpm-rate-limits.mintlify.site/developer-guide/sdk-guide/quickstart.md): Install a Fish Audio SDK, authenticate, and generate your first audio in under a minute
- [Docker Deployment](https://hanabiaiinc-docs-concurrency-qpm-rate-limits.mintlify.site/developer-guide/self-hosting/docker-deployment.md): Deploy Fish Audio models using Docker containers
- [Local Model Setup](https://hanabiaiinc-docs-concurrency-qpm-rate-limits.mintlify.site/developer-guide/self-hosting/local-setup.md): Install and configure Fish Audio models for local inference
- [Running Inference](https://hanabiaiinc-docs-concurrency-qpm-rate-limits.mintlify.site/developer-guide/self-hosting/running-inference.md): Generate speech using self-hosted Fish Audio models
- [Manage Voices](https://hanabiaiinc-docs-concurrency-qpm-rate-limits.mintlify.site/features/manage-voices.md): List, inspect, update, and delete your voice models
- [Realtime Streaming](https://hanabiaiinc-docs-concurrency-qpm-rate-limits.mintlify.site/features/realtime-streaming.md): Stream audio as it generates for the lowest latency
- [Speech to Text](https://hanabiaiinc-docs-concurrency-qpm-rate-limits.mintlify.site/features/speech-to-text.md): Transcribe audio to text with per-segment timestamps
- [Text to Speech](https://hanabiaiinc-docs-concurrency-qpm-rate-limits.mintlify.site/features/text-to-speech.md): Turn text into lifelike speech — use it however you build
- [Voice Cloning](https://hanabiaiinc-docs-concurrency-qpm-rate-limits.mintlify.site/features/voice-cloning.md): Create a custom voice from audio samples, then speak with it
- [Voice Design](https://hanabiaiinc-docs-concurrency-qpm-rate-limits.mintlify.site/features/voice-design.md): Generate candidate voices from a prompt
- [Overview](https://hanabiaiinc-docs-concurrency-qpm-rate-limits.mintlify.site/overview/capabilities.md): Everything Fish Audio can do — and how to build with it
- [Platform (Web App)](https://hanabiaiinc-docs-concurrency-qpm-rate-limits.mintlify.site/overview/platform.md): Use Fish Audio in your browser — no code required