# Fish Audio

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

- [Overview](https://docs.fish.audio/overview/capabilities.md): Everything Fish Audio can do, and how to build with it
- [Get Your API Key](https://docs.fish.audio/developer-guide/getting-started/api-key.md): Create a Fish Audio account, generate an API key, and make your first request
- [Quick Start](https://docs.fish.audio/developer-guide/getting-started/quickstart.md): Generate your first AI voice with Fish Audio in under 5 minutes
- [Migrate to Fish Audio](https://docs.fish.audio/developer-guide/getting-started/migration.md): Run your existing OpenAI, OpenRouter, ElevenLabs, or Groq code on Fish Audio.
- [Coding Assistant Quickstart](https://docs.fish.audio/developer-guide/resources/agent-quickstart.md): Build with Fish Audio using your AI coding assistant: install the skill and start prompting in a minute
- [Changelog](https://docs.fish.audio/developer-guide/getting-started/changelog.md): Complete release history and version updates for all Fish Audio products
- [Text to Speech](https://docs.fish.audio/features/text-to-speech.md): Turn text into lifelike speech
- [Drama 3](https://docs.fish.audio/features/text-to-speech/drama-3.md): Text-to-speech model you can direct
- [Emotion Control](https://docs.fish.audio/developer-guide/core-features/emotions.md): Add natural emotions and expressions to your AI-generated speech
- [Fine-grained Control](https://docs.fish.audio/developer-guide/core-features/fine-grained-control.md): Advanced control over speech generation
- [Pronunciation Dictionaries](https://docs.fish.audio/developer-guide/core-features/fine-grained-control/pronunciation-dictionaries.md): Create, preview, and publish pronunciation dictionaries in the web app and use them in TTS requests
- [English Phoneme Control](https://docs.fish.audio/developer-guide/core-features/fine-grained-control/english.md): Control English pronunciation with CMU Arpabet
- [Chinese Phoneme Control](https://docs.fish.audio/developer-guide/core-features/fine-grained-control/chinese.md): Control Chinese pronunciation with tone-number pinyin
- [Japanese Phoneme Control](https://docs.fish.audio/developer-guide/core-features/fine-grained-control/japanese.md): Control Japanese pronunciation with romaji phonemes and pitch accent markers
- [Speech to Text](https://docs.fish.audio/features/speech-to-text.md): Transcribe audio with transcribe-1-pro, including word-level timestamps, speaker turns for multi-speaker conversations, long recordings, and emotion cues
- [Realtime Speech to Text](https://docs.fish.audio/features/speech-to-text/realtime.md): Transcribe live audio turn by turn with transcribe-stream-1: turn detection that knows when the user has finished, backchannel and background awareness, and conversation context
- [Voice Design](https://docs.fish.audio/features/voice-design.md): Generate candidate voices from a prompt
- [Voice Cloning](https://docs.fish.audio/features/voice-cloning.md): Create a custom voice from audio samples, then speak with it
- [Realtime Streaming](https://docs.fish.audio/features/realtime-streaming.md): Stream audio as it generates for the lowest latency
- [Manage Voices](https://docs.fish.audio/features/manage-voices.md): List, inspect, update, and delete your voice models
- [Platform (Web App)](https://docs.fish.audio/overview/platform.md): Use Fish Audio in your browser, no code required
- [Professional Voice Clone](https://docs.fish.audio/overview/platform/create-voice/professional-voice-clone.md): Clone a real, verified voice at studio quality in the Fish Audio web app, then release it
- [Voice Design in the Web App](https://docs.fish.audio/overview/platform/create-voice/voice-design.md): Generate a custom voice from a text description in the Fish Audio web app
- [MCP Server](https://docs.fish.audio/overview/mcp.md): Connect Claude, Cursor, or another MCP client to your Fish Audio account for voices, speech, images, video, and Story Studio
- [MCP Tools](https://docs.fish.audio/overview/mcp/tools.md): What each tool on the Fish Audio MCP server does, grouped by area
- [Models Overview](https://docs.fish.audio/developer-guide/models-pricing/models-overview.md): Explore Fish Audio's speech generation and transcription models and their capabilities
- [Choosing a Model](https://docs.fish.audio/developer-guide/models-pricing/choosing-a-model.md): Select the right Fish Audio model for your use case and requirements
- [Model Deprecations](https://docs.fish.audio/developer-guide/models-pricing/deprecations.md): Track deprecated models and migration timelines for Fish Audio services
- [Migrate from S1](https://docs.fish.audio/developer-guide/models-pricing/migrate-from-s1.md): Fish Audio S1 will be retired on December 31, 2026. Move your text-to-speech requests from s1 to s2.1-pro.
- [Pricing & Rate Limits](https://docs.fish.audio/developer-guide/models-pricing/pricing-and-rate-limits.md): Understand Fish Audio pricing plans, usage costs, and API rate limits
- [Agents Overview](https://docs.fish.audio/agents/overview.md): Build voice agents in the console, ship them with the REST API and SDKs, and put them on the phone
- [Quickstart](https://docs.fish.audio/agents/quickstart.md): Create a voice agent and have your first conversation in minutes
- [Core Concepts](https://docs.fish.audio/agents/concepts.md): Workspaces, agents, versions, and sessions: the mental model behind Fish Agents
- [Pricing](https://docs.fish.audio/agents/pricing.md): Rates for conversations, LLM usage, telephony, transfers, and simulation tests, plus the trial balance and billing
- [Configuration](https://docs.fish.audio/agents/build/configuration.md): Set your agent's system prompt, first message, and conversation behavior, in the Builder or through the API
- [Voice & Language](https://docs.fish.audio/agents/build/voice-language.md): Choose the voice your agent speaks with and the language it converses in
- [Time & Timezone](https://docs.fish.audio/agents/build/time-timezone.md): Let your agent know the current date and time: the switch, how the timezone is chosen, and per-session overrides
- [Knowledge Base](https://docs.fish.audio/agents/build/knowledge-base.md): Ground your agent in your own documents: add a source once, attach it to any agent in your workspace
- [Tools](https://docs.fish.audio/agents/build/tools.md): Give your agent the ability to act during a conversation: call your backend, trigger actions in your app, or use built-in capabilities
- [Webhook Tools](https://docs.fish.audio/agents/build/webhook-tools.md): Let your agent call your HTTP endpoints in the middle of a conversation
- [Client Tools](https://docs.fish.audio/agents/build/client-tools.md): Let the agent trigger actions in your own app: declared on the agent, executed by your code through the SDK
- [System Tools](https://docs.fish.audio/agents/build/system-tools.md): Built-in agent capabilities like hanging up the call, enabled per agent
- [Dynamic Variables](https://docs.fish.audio/agents/build/dynamic-variables.md): Personalize each session with template variables: your own values, and facts the platform fills in
- [Custom LLM](https://docs.fish.audio/agents/build/custom-llm.md): Serve your agent's replies from your own OpenAI-compatible model endpoint
- [Preview Calls](https://docs.fish.audio/agents/test/preview-calls.md): Talk to your draft agent in a live voice call, right in the Builder
- [Agent Tests](https://docs.fish.audio/agents/test/agent-tests.md): Script a conversation or simulate a user, then let an LLM judge score your agent to catch regressions before you publish
- [Import and Export Tests](https://docs.fish.audio/agents/test/import-export-tests.md): Save tests as JSON files, recreate them in the same team, or move them to another team over the API
- [Tutorial: Simulate a Rescheduling Call](https://docs.fish.audio/agents/test/simulation-tutorial.md): Build a Simulation test step by step, from the scenario to tool mocks and assertions, and read what its results tell you
- [Deploy Your Agent](https://docs.fish.audio/agents/deploy/overview.md): Choose where users meet your agent and who may start sessions: widget, SDKs, or phone; public or authenticated
- [Versions & Publishing](https://docs.fish.audio/agents/deploy/versions-publishing.md): Edit safely in a draft, then publish an immutable version that live sessions run
- [Public Agents](https://docs.fish.audio/agents/deploy/public-agents.md): Let visitors talk to your agent directly from the browser, no backend required
- [Authenticated Sessions](https://docs.fish.audio/agents/deploy/authenticated-sessions.md): Create short-lived session tokens on your backend and run private agents in any client
- [Widget](https://docs.fish.audio/agents/deploy/widget.md): Embed a complete voice and chat UI on any website with two lines of HTML, no build step
- [Web SDK](https://docs.fish.audio/agents/deploy/web-sdk.md): Voice sessions in the browser with @fishaudio/agent-client: options, events, transcripts, text input, audio controls, client tools, and errors
- [React SDK](https://docs.fish.audio/agents/deploy/react-sdk.md): Add voice conversations to your React app with hooks and drop-in components
- [Wire Protocol](https://docs.fish.audio/agents/deploy/protocol.md): The realtime message contract between clients and agent sessions, for platforms the SDKs don't cover
- [Phone Numbers](https://docs.fish.audio/agents/telephony/phone-numbers.md): Search, purchase, bind, and release phone numbers for your agents over the REST API
- [Bring Your Own Number](https://docs.fish.audio/agents/telephony/byo-sip.md): Import a number you already own by pointing your carrier's SIP trunk at Fish Audio: no rental fee, no telephony charges
- [Inbound Calls](https://docs.fish.audio/agents/telephony/inbound-calls.md): Bind an agent to a phone number and it answers every call to that number
- [Outbound Calls](https://docs.fish.audio/agents/telephony/outbound-calls.md): Place calls from your phone numbers over the API; the agent speaks when the callee answers
- [Call Transfers](https://docs.fish.audio/agents/telephony/transfers.md): Let the agent hand a phone call to a human: a cold carrier handoff, or a warm transfer with hold music and a private briefing
- [Keypad Menu and Input](https://docs.fish.audio/agents/telephony/keypad.md): Let phone callers use their keypad: a menu before the agent's first reply, and digits typed during the call
- [Conversation History](https://docs.fish.audio/agents/monitor/conversation-history.md): List past sessions, replay the full timeline of messages and tool calls, and download recordings
- [Post-call Analysis](https://docs.fish.audio/agents/monitor/post-call-analysis.md): Automatic summaries, structured data extraction, and success evaluation after every conversation
- [Webhooks](https://docs.fish.audio/agents/monitor/webhooks.md): Get an HTTP POST when a call ends and when its analysis settles, and personalize inbound phone calls before the agent answers
- [SDK Quickstart](https://docs.fish.audio/developer-guide/sdk-guide/quickstart.md): Install a Fish Audio SDK, authenticate, and generate your first audio in under a minute
- [Authentication](https://docs.fish.audio/developer-guide/sdk-guide/python/authentication.md): Configure API authentication for the Fish Audio Python SDK
- [Errors & Retries](https://docs.fish.audio/developer-guide/sdk-guide/python/errors.md): Exception types, retry strategy, and timeouts in the Fish Audio Python SDK
- [Stream TTS to a file](https://docs.fish.audio/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://docs.fish.audio/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://docs.fish.audio/developer-guide/sdk-guide/cookbook/transcribe-to-captions.md): Transcribe audio with word-level timestamps, group the words into caption cues, and write valid SRT and WebVTT files
- [Batch-transcribe files with a language hint](https://docs.fish.audio/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
- [Transcribe a live audio stream in realtime](https://docs.fish.audio/developer-guide/sdk-guide/cookbook/realtime-transcription.md): Stream audio to transcribe-stream-1 over a WebSocket and print drafts, turn events and final transcripts as they arrive
- [Instant voice cloning](https://docs.fish.audio/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
- [Clone a voice and wait until it is ready](https://docs.fish.audio/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
- [One-shot vs persistent cloning: pick the right approach](https://docs.fish.audio/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://docs.fish.audio/developer-guide/sdk-guide/cookbook/realtime-llm-to-speech.md): Pipe a streaming LLM response straight into speech over a WebSocket as tokens arrive
- [Build a voice agent loop: speech in, reply, speech out](https://docs.fish.audio/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
- [Build a realtime voice agent: streaming speech in, reply, speech out](https://docs.fish.audio/developer-guide/sdk-guide/cookbook/realtime-voice-agent.md): Use realtime speech to text to know when the user has finished, start replies early, keep talking through backchannels and stop on interruptions
- [Discover and reuse a Voice Library voice](https://docs.fish.audio/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
- [Voice Cloning Best Practices](https://docs.fish.audio/developer-guide/best-practices/voice-cloning.md): Simple tips to get the best voice cloning results with Fish Audio
- [Emotion & Expression Control](https://docs.fish.audio/developer-guide/best-practices/emotion-control.md): Make your AI voices express emotions naturally
- [Real-time Voice Streaming](https://docs.fish.audio/developer-guide/best-practices/real-time-streaming.md): Stream voice generation in real-time for interactive applications
- [Pipecat](https://docs.fish.audio/developer-guide/integrations/pipecat.md): Build voice AI agents with Fish Audio and Pipecat
- [LiveKit](https://docs.fish.audio/developer-guide/integrations/livekit.md): Build real-time voice AI agents with Fish Audio and LiveKit
- [n8n](https://docs.fish.audio/developer-guide/integrations/n8n.md): Automate workflows with Fish Audio and n8n
- [Telnyx](https://docs.fish.audio/developer-guide/integrations/telnyx.md): Use Fish Audio voices for real-time and in-call text-to-speech with Telnyx
- [SLNG](https://docs.fish.audio/developer-guide/integrations/slng.md): Access Fish Audio's real-time speech models through SLNG, our preferred regional hosting provider
- [Migrate from OpenAI](https://docs.fish.audio/developer-guide/compat/migrate-from-openai.md): Point the official OpenAI SDKs at Fish Audio: speech, transcription, chat-modality audio, and the Realtime WebSocket.
- [Migrate from OpenRouter](https://docs.fish.audio/developer-guide/compat/migrate-from-openrouter.md): Point the official OpenRouter TypeScript SDK at Fish Audio: TTS, STT, and the model catalog.
- [Migrate from ElevenLabs](https://docs.fish.audio/developer-guide/compat/migrate-from-elevenlabs.md): Point the ElevenLabs SDK at Fish Audio: TTS, timestamps, realtime streaming input, speech-to-text, and your voice library.
- [Migrate from Groq](https://docs.fish.audio/developer-guide/compat/migrate-from-groq.md): Point the official Groq SDKs at Fish Audio: TTS, transcription, and the model catalog.
- [Compatibility](https://docs.fish.audio/developer-guide/compat/capabilities.md): The compatibility contract: supported endpoints, how parameters behave, and exactly what is refused.
- [Realtime protocol reference](https://docs.fish.audio/developer-guide/compat/realtime-protocol.md): What the OpenAI-compatible Realtime WebSocket speaks: events, formats, turn detection, and transcription sessions.
- [Introduction](https://docs.fish.audio/developer-guide/self-hosting/introduction.md): Run the Fish Audio Enterprise speech stack inside your own infrastructure
- [Requirements](https://docs.fish.audio/developer-guide/self-hosting/requirements.md): Hardware, platform, and network baselines for a self-hosted deployment
- [Registry & license](https://docs.fish.audio/developer-guide/self-hosting/registry-access.md): The Self Host dashboard: deploy tokens, registry sign-in, and your license bundle
- [Kubernetes deployment](https://docs.fish.audio/developer-guide/self-hosting/kubernetes.md): What the Helm delivery installs, what you decide before installing, and what to expect
- [All-in-One container](https://docs.fish.audio/developer-guide/self-hosting/all-in-one.md): The single-container appliance: what it is, what it cannot do, and what running it involves
- [Air-gapped deployments](https://docs.fish.audio/developer-guide/self-hosting/air-gapped.md): Running Fish Audio Enterprise on a network that cannot reach Fish Audio at all
- [Operations](https://docs.fish.audio/developer-guide/self-hosting/operations.md): Monitoring, scaling, backups, and troubleshooting for a self-hosted deployment
- [Releases](https://docs.fish.audio/developer-guide/self-hosting/enterprise-releases.md): How Fish Audio Enterprise versions are identified and how to move between them
- [AI Coding Assistants](https://docs.fish.audio/developer-guide/resources/coding-agents.md): Install the Fish Audio skill so your coding agent writes correct SDK and API code
- [Contributing](https://docs.fish.audio/contributing.md): Help improve Fish Audio and contribute to our open source projects.
- [Brand Guidelines](https://docs.fish.audio/developer-guide/resources/brand.md): Design guidelines for using Fish Audio brand assets
- [Introduction](https://docs.fish.audio/api-reference/introduction.md): How to use the Fish Audio API
- [Tracing & Performance Analysis](https://docs.fish.audio/api-reference/observability.md): Correlate Fish Audio inference spans with your own distributed traces
- [Errors](https://docs.fish.audio/api-reference/errors.md): HTTP status codes, the error response shape, and how to handle them in any language
- [Get API Credit](https://docs.fish.audio/api-reference/endpoint/wallet/get-api-credit.md): Get current API credit balance
- [Get User Package](https://docs.fish.audio/api-reference/endpoint/wallet/get-user-package.md): Get current user premium information
- [List Models](https://docs.fish.audio/api-reference/endpoint/model/list-models.md): Get a list of all models
- [Create Model](https://docs.fish.audio/api-reference/endpoint/model/create-model.md): Create a new voice model
- [Get Model](https://docs.fish.audio/api-reference/endpoint/model/get-model.md): Get details of a specific model
- [Delete Model](https://docs.fish.audio/api-reference/endpoint/model/delete-model.md): Delete an existing model
- [Update Model](https://docs.fish.audio/api-reference/endpoint/model/update-model.md): Update an existing model
- [Text to Speech](https://docs.fish.audio/api-reference/endpoint/openapi-v1/text-to-speech.md): Convert text to speech
- [Text to Speech Stream with Timestamps](https://docs.fish.audio/api-reference/endpoint/openapi-v1/text-to-speech-stream-with-timestamps.md): Stream generated speech with timestamp alignment snapshots
- [WebSocket TTS Streaming](https://docs.fish.audio/api-reference/endpoint/websocket/tts-live.md): Real-time text-to-speech streaming via WebSocket
- [WebSocket TTS with Timestamps](https://docs.fish.audio/api-reference/endpoint/openapi-v1/text-to-speech-live-with-timestamps.md): Stream text and receive speech with word-level timestamps over WebSocket
- [Speech to Text](https://docs.fish.audio/api-reference/endpoint/openapi-v1/speech-to-text.md): Transcribe audio with transcribe-1-pro, the recommended speech-to-text model: request and response fields, speaker turns, limits, formats, and errors
- [WebSocket Realtime Speech to Text](https://docs.fish.audio/api-reference/endpoint/websocket/asr-realtime.md): Stream audio over a WebSocket and receive transcripts turn by turn, with turn detection, live drafts and conversation context
- [Voice Design](https://docs.fish.audio/api-reference/endpoint/openapi-v1/voice-design.md): Generate candidate voices from a prompt
- [Agents API Errors](https://docs.fish.audio/api-reference/agent-errors.md): Status codes, error shapes, and recovery guidance for every /v1/agent endpoint
- [List Agents](https://docs.fish.audio/api-reference/endpoint/agent/list-agents.md): List your team's agents, newest first.
- [Create Agent](https://docs.fish.audio/api-reference/endpoint/agent/create-agent.md): Create an agent, optionally with its full initial configuration inline — one call provisions a ready-to-publish agent.
- [Get Agent](https://docs.fish.audio/api-reference/endpoint/agent/get-agent.md): Fetch one agent's profile fields.
- [Update Agent](https://docs.fish.audio/api-reference/endpoint/agent/update-agent.md): Update agent-level fields (name, description, status, public access and session-override policy).
- [Delete Agent](https://docs.fish.audio/api-reference/endpoint/agent/delete-agent.md): Delete an agent together with its configuration and version history. Existing session records are retained.
- [Get Draft Config](https://docs.fish.audio/api-reference/endpoint/agent/get-draft-config.md): Read the agent's current draft configuration — the state the next publish will freeze.
- [Update Draft Config](https://docs.fish.audio/api-reference/endpoint/agent/update-draft-config.md): Patch the draft configuration section by section; omitted sections keep their value.
- [Publish Agent](https://docs.fish.audio/api-reference/endpoint/agent/publish-agent.md): Freeze the current draft into an immutable version (version_number auto-increments) and make it the live configuration for new sessions.
- [List Agent Versions](https://docs.fish.audio/api-reference/endpoint/agent/list-agent-versions.md): The publish history, newest first.
- [Get Agent Version](https://docs.fish.audio/api-reference/endpoint/agent/get-agent-version.md): One published version with its full frozen configuration snapshot — including the current live version.
- [Get Widget Config](https://docs.fish.audio/api-reference/endpoint/agent/get-widget-config.md): Unauthenticated display configuration for the embeddable `<fish-agent>` widget.
- [Create Agent Session](https://docs.fish.audio/api-reference/endpoint/agent/create-agent-session.md): Start a conversation session with an agent and receive a join token for the session transport (currently LiveKit WebRTC).
- [List Agent Sessions](https://docs.fish.audio/api-reference/endpoint/agent/list-agent-sessions.md): List your team's sessions, newest first.
- [Get Agent Session](https://docs.fish.audio/api-reference/endpoint/agent/get-agent-session.md): Fetch one session's full detail: status, timing, and the conversation timeline (transcript turns interleaved with tool calls, in order).
- [Get Agent Session Recording](https://docs.fish.audio/api-reference/endpoint/agent/get-agent-session-recording.md): Return time-limited download URLs for the session's audio recording, one per speaker track (agent and user are recorded separately).
- [End Agent Session](https://docs.fish.audio/api-reference/endpoint/agent/end-agent-session.md): Hang up a live session: the agent disconnects and the call terminates.
- [List Tools](https://docs.fish.audio/api-reference/endpoint/agent/list-tools.md): List your team's tools, newest first.
- [Create Tool](https://docs.fish.audio/api-reference/endpoint/agent/create-tool.md): Create a workspace tool.
- [Get Tool](https://docs.fish.audio/api-reference/endpoint/agent/get-tool.md): Fetch one tool's full definition.
- [Update Tool](https://docs.fish.audio/api-reference/endpoint/agent/update-tool.md): Patch tool fields; omitted fields keep their value (null is rejected — send an empty string to clear a text field).
- [Delete Tool](https://docs.fish.audio/api-reference/endpoint/agent/delete-tool.md): Delete a tool.
- [List Agents Using Tool](https://docs.fish.audio/api-reference/endpoint/agent/list-agents-using-tool.md): Every agent whose draft configuration references this tool — the pre-flight check before a delete.
- [List Tests](https://docs.fish.audio/api-reference/endpoint/agent/list-tests.md): List your team's tests, newest first.
- [Create Test](https://docs.fish.audio/api-reference/endpoint/agent/create-test.md): Create a Single Turn, Tool or Simulation test, optionally attached to agents.
- [Get Test](https://docs.fish.audio/api-reference/endpoint/agent/get-test.md): Fetch one test's full definition, which is also the export format.
- [Update Test](https://docs.fish.audio/api-reference/endpoint/agent/update-test.md): Patch test fields. Omitted fields keep their value.
- [Delete Test](https://docs.fish.audio/api-reference/endpoint/agent/delete-test.md): Delete a test and detach it from every agent.
- [Attach Test](https://docs.fish.audio/api-reference/endpoint/agent/attach-test.md): Attach a test to an agent so the agent's test runs include it.
- [Detach Test](https://docs.fish.audio/api-reference/endpoint/agent/detach-test.md): Detach a test from an agent. The test stays in your library.
- [List Test Tools](https://docs.fish.audio/api-reference/endpoint/agent/list-test-tools.md): The tool ids a test can reference for this agent.
- [Run Tests](https://docs.fish.audio/api-reference/endpoint/agent/run-tests.md): Start a batch that runs the agent's attached tests against its draft.
- [List Test Batches](https://docs.fish.audio/api-reference/endpoint/agent/list-test-batches.md): The agent's test batches, newest first, with their counts.
- [Get Test Batch](https://docs.fish.audio/api-reference/endpoint/agent/get-test-batch.md): The runs of one batch with their pass, fail and error counts.
- [List Test Runs](https://docs.fish.audio/api-reference/endpoint/agent/list-test-runs.md): List your team's test runs, newest first.
- [Get Test Run](https://docs.fish.audio/api-reference/endpoint/agent/get-test-run.md): Fetch one test run with its transcript, verdicts and tool calls.
- [List Knowledge Sources](https://docs.fish.audio/api-reference/endpoint/agent/list-knowledge-sources.md): List your team's knowledge sources, newest first.
- [Create Knowledge Source](https://docs.fish.audio/api-reference/endpoint/agent/create-knowledge-source.md): Upload a plain-text or Markdown file (UTF-8, up to 1 MB) as a knowledge source.
- [Get Knowledge Source](https://docs.fish.audio/api-reference/endpoint/agent/get-knowledge-source.md): Fetch one knowledge source including its full text content and current revision number.
- [Update Knowledge Source](https://docs.fish.audio/api-reference/endpoint/agent/update-knowledge-source.md): Rename the source and/or replace its content by uploading a new file in `source` (multipart).
- [Delete Knowledge Source](https://docs.fish.audio/api-reference/endpoint/agent/delete-knowledge-source.md): Delete a knowledge source.
- [List Agents Using Knowledge Source](https://docs.fish.audio/api-reference/endpoint/agent/list-agents-using-knowledge-source.md): Every agent that references this source in its draft or currently published configuration — the pre-flight check before a delete.
- [Search Available Phone Numbers](https://docs.fish.audio/api-reference/endpoint/agent/search-available-phone-numbers.md): Search the purchasable number inventory.
- [List Phone Numbers](https://docs.fish.audio/api-reference/endpoint/agent/list-phone-numbers.md): List your team's phone numbers, newest first.
- [Purchase Phone Number](https://docs.fish.audio/api-reference/endpoint/agent/purchase-phone-number.md): Buy a number from the inventory.
- [Get Phone Number](https://docs.fish.audio/api-reference/endpoint/agent/get-phone-number.md): Fetch one phone number, including its current agent binding and provisioning status.
- [Update Phone Number](https://docs.fish.audio/api-reference/endpoint/agent/update-phone-number.md): Change the label and/or repoint the number at another agent — the deployment-pipeline move (rebind from the staging agent to the production one).
- [Release Phone Number](https://docs.fish.audio/api-reference/endpoint/agent/release-phone-number.md): Release a number back to the provider's inventory and stop its daily billing.
- [Create Phone Call](https://docs.fish.audio/api-reference/endpoint/agent/create-phone-call.md): Place an outbound call from one of your phone numbers; the agent speaks when the callee answers.
- [Overview](https://docs.fish.audio/api-reference/sdk/python/overview.md): Fish Audio Python SDK for text-to-speech and voice cloning
- [Client](https://docs.fish.audio/api-reference/sdk/python/client.md)
- [Resources](https://docs.fish.audio/api-reference/sdk/python/resources.md)
- [Types](https://docs.fish.audio/api-reference/sdk/python/types.md)
- [Core](https://docs.fish.audio/api-reference/sdk/python/core.md)
- [Utils](https://docs.fish.audio/api-reference/sdk/python/utils.md)
- [Exceptions](https://docs.fish.audio/api-reference/sdk/python/exceptions.md)
- [Legacy](https://docs.fish.audio/archive/python-sdk-legacy/index.md): Archived documentation for the legacy Session-based Python SDK
- [JavaScript SDK Reference](https://docs.fish.audio/api-reference/sdk/javascript/api-reference.md): Complete reference for Fish Audio JavaScript SDK

## OpenAPI Specs

- [openapi](/api-reference/openapi.json)
- [openapi](/temp/api-reference/openapi.json)

## AsyncAPI Specs

- [asyncapi-asr-realtime](/api-reference/asyncapi-asr-realtime.yml)
- [asyncapi](/api-reference/asyncapi.yml)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.